Commit
•
f4f3f57
1
Parent(s):
9e2403f
Upload 19 files
Browse files- added_tokens.json +108 -0
- all_results.json +13 -0
- config.json +41 -0
- eval_results.json +9 -0
- label.txt +1 -0
- merges.txt +0 -0
- normalizer.json +1742 -0
- pred.txt +1 -0
- preprocessor_config.json +0 -0
- pytorch_model.bin +3 -0
- run.sh +34 -0
- run_speech_recognition_seq2seq_streaming.py +617 -0
- ryNormText.py +81 -0
- special_tokens_map.json +133 -0
- tokenizer_config.json +36 -0
- train_results.json +7 -0
- trainer_state.json +1275 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|af|>": 50327,
|
| 3 |
+
"<|am|>": 50334,
|
| 4 |
+
"<|ar|>": 50272,
|
| 5 |
+
"<|as|>": 50350,
|
| 6 |
+
"<|az|>": 50304,
|
| 7 |
+
"<|ba|>": 50355,
|
| 8 |
+
"<|be|>": 50330,
|
| 9 |
+
"<|bg|>": 50292,
|
| 10 |
+
"<|bn|>": 50302,
|
| 11 |
+
"<|bo|>": 50347,
|
| 12 |
+
"<|br|>": 50309,
|
| 13 |
+
"<|bs|>": 50315,
|
| 14 |
+
"<|ca|>": 50270,
|
| 15 |
+
"<|cs|>": 50283,
|
| 16 |
+
"<|cy|>": 50297,
|
| 17 |
+
"<|da|>": 50285,
|
| 18 |
+
"<|de|>": 50261,
|
| 19 |
+
"<|el|>": 50281,
|
| 20 |
+
"<|en|>": 50259,
|
| 21 |
+
"<|es|>": 50262,
|
| 22 |
+
"<|et|>": 50307,
|
| 23 |
+
"<|eu|>": 50310,
|
| 24 |
+
"<|fa|>": 50300,
|
| 25 |
+
"<|fi|>": 50277,
|
| 26 |
+
"<|fo|>": 50338,
|
| 27 |
+
"<|fr|>": 50265,
|
| 28 |
+
"<|gl|>": 50319,
|
| 29 |
+
"<|gu|>": 50333,
|
| 30 |
+
"<|haw|>": 50352,
|
| 31 |
+
"<|ha|>": 50354,
|
| 32 |
+
"<|he|>": 50279,
|
| 33 |
+
"<|hi|>": 50276,
|
| 34 |
+
"<|hr|>": 50291,
|
| 35 |
+
"<|ht|>": 50339,
|
| 36 |
+
"<|hu|>": 50286,
|
| 37 |
+
"<|hy|>": 50312,
|
| 38 |
+
"<|id|>": 50275,
|
| 39 |
+
"<|is|>": 50311,
|
| 40 |
+
"<|it|>": 50274,
|
| 41 |
+
"<|ja|>": 50266,
|
| 42 |
+
"<|jw|>": 50356,
|
| 43 |
+
"<|ka|>": 50329,
|
| 44 |
+
"<|kk|>": 50316,
|
| 45 |
+
"<|km|>": 50323,
|
| 46 |
+
"<|kn|>": 50306,
|
| 47 |
+
"<|ko|>": 50264,
|
| 48 |
+
"<|la|>": 50294,
|
| 49 |
+
"<|lb|>": 50345,
|
| 50 |
+
"<|ln|>": 50353,
|
| 51 |
+
"<|lo|>": 50336,
|
| 52 |
+
"<|lt|>": 50293,
|
| 53 |
+
"<|lv|>": 50301,
|
| 54 |
+
"<|mg|>": 50349,
|
| 55 |
+
"<|mi|>": 50295,
|
| 56 |
+
"<|mk|>": 50308,
|
| 57 |
+
"<|ml|>": 50296,
|
| 58 |
+
"<|mn|>": 50314,
|
| 59 |
+
"<|mr|>": 50320,
|
| 60 |
+
"<|ms|>": 50282,
|
| 61 |
+
"<|mt|>": 50343,
|
| 62 |
+
"<|my|>": 50346,
|
| 63 |
+
"<|ne|>": 50313,
|
| 64 |
+
"<|nl|>": 50271,
|
| 65 |
+
"<|nn|>": 50342,
|
| 66 |
+
"<|nocaptions|>": 50362,
|
| 67 |
+
"<|notimestamps|>": 50363,
|
| 68 |
+
"<|no|>": 50288,
|
| 69 |
+
"<|oc|>": 50328,
|
| 70 |
+
"<|pa|>": 50321,
|
| 71 |
+
"<|pl|>": 50269,
|
| 72 |
+
"<|ps|>": 50340,
|
| 73 |
+
"<|pt|>": 50267,
|
| 74 |
+
"<|ro|>": 50284,
|
| 75 |
+
"<|ru|>": 50263,
|
| 76 |
+
"<|sa|>": 50344,
|
| 77 |
+
"<|sd|>": 50332,
|
| 78 |
+
"<|si|>": 50322,
|
| 79 |
+
"<|sk|>": 50298,
|
| 80 |
+
"<|sl|>": 50305,
|
| 81 |
+
"<|sn|>": 50324,
|
| 82 |
+
"<|so|>": 50326,
|
| 83 |
+
"<|sq|>": 50317,
|
| 84 |
+
"<|sr|>": 50303,
|
| 85 |
+
"<|startoflm|>": 50360,
|
| 86 |
+
"<|startofprev|>": 50361,
|
| 87 |
+
"<|startoftranscript|>": 50258,
|
| 88 |
+
"<|su|>": 50357,
|
| 89 |
+
"<|sv|>": 50273,
|
| 90 |
+
"<|sw|>": 50318,
|
| 91 |
+
"<|ta|>": 50287,
|
| 92 |
+
"<|te|>": 50299,
|
| 93 |
+
"<|tg|>": 50331,
|
| 94 |
+
"<|th|>": 50289,
|
| 95 |
+
"<|tk|>": 50341,
|
| 96 |
+
"<|tl|>": 50348,
|
| 97 |
+
"<|transcribe|>": 50359,
|
| 98 |
+
"<|translate|>": 50358,
|
| 99 |
+
"<|tr|>": 50268,
|
| 100 |
+
"<|tt|>": 50351,
|
| 101 |
+
"<|uk|>": 50280,
|
| 102 |
+
"<|ur|>": 50290,
|
| 103 |
+
"<|uz|>": 50337,
|
| 104 |
+
"<|vi|>": 50278,
|
| 105 |
+
"<|yi|>": 50335,
|
| 106 |
+
"<|yo|>": 50325,
|
| 107 |
+
"<|zh|>": 50260
|
| 108 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.05,
|
| 3 |
+
"eval_cer": 123.45306368849984,
|
| 4 |
+
"eval_loss": 3.212874174118042,
|
| 5 |
+
"eval_runtime": 303.2793,
|
| 6 |
+
"eval_samples_per_second": 3.251,
|
| 7 |
+
"eval_steps_per_second": 1.626,
|
| 8 |
+
"eval_wer": 118.50381679389312,
|
| 9 |
+
"train_loss": 3.0522214595794677,
|
| 10 |
+
"train_runtime": 5458.8622,
|
| 11 |
+
"train_samples_per_second": 1.832,
|
| 12 |
+
"train_steps_per_second": 0.916
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-large-v2",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": [
|
| 10 |
+
220,
|
| 11 |
+
50257
|
| 12 |
+
],
|
| 13 |
+
"bos_token_id": 50257,
|
| 14 |
+
"d_model": 1280,
|
| 15 |
+
"decoder_attention_heads": 20,
|
| 16 |
+
"decoder_ffn_dim": 5120,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 32,
|
| 19 |
+
"decoder_start_token_id": 50258,
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"encoder_attention_heads": 20,
|
| 22 |
+
"encoder_ffn_dim": 5120,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 32,
|
| 25 |
+
"eos_token_id": 50257,
|
| 26 |
+
"forced_decoder_ids": null,
|
| 27 |
+
"init_std": 0.02,
|
| 28 |
+
"is_encoder_decoder": true,
|
| 29 |
+
"max_length": 448,
|
| 30 |
+
"max_source_positions": 1500,
|
| 31 |
+
"max_target_positions": 448,
|
| 32 |
+
"model_type": "whisper",
|
| 33 |
+
"num_hidden_layers": 32,
|
| 34 |
+
"num_mel_bins": 80,
|
| 35 |
+
"pad_token_id": 50257,
|
| 36 |
+
"scale_embedding": false,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.25.1",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 51865
|
| 41 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.05,
|
| 3 |
+
"eval_cer": 123.45306368849984,
|
| 4 |
+
"eval_loss": 3.212874174118042,
|
| 5 |
+
"eval_runtime": 303.2793,
|
| 6 |
+
"eval_samples_per_second": 3.251,
|
| 7 |
+
"eval_steps_per_second": 1.626,
|
| 8 |
+
"eval_wer": 118.50381679389312
|
| 9 |
+
}
|
label.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
label_str=['心 理 性 別 ', '火 燒 尻 川 ', '草 仔 色 ', '十 三 行 ', '水 里 鄉 ', '這 搭 有 一 个 大 商 場 ', '聯 合 國 ', '菜 頭 籠 仔 ', '辣 椒 ', '肉 筋 ', '新 興 區 ', '癩 疒 哥 病 ', '覕 冬 ', '摧 仔 ', '西 藥 房 ', '心 碎 ', '燒 包 仔 ', '通 敨 ', '皇 軍 ', '濁 水 溪 出 代 誌 ', '粗 細 ', '哀 哼 ', '九 年 一 貫 ', '精 靈 ', '三 寶 ', '速 速 ', '坐 疶 咧 等 ', '儑 目 袂 曉 看 懸 低 ', '圳 後 ', '兩 个 人 已 經 講 和 矣 ', '足 媠 ', '細 空 喙 ', '掠 著 根 頭 ', '茨 城 縣 ', '概 率 ', '草 人 坑 ', '祝 你 生 日 快 樂 ', '坑 崁 ', '出 水 ', '咇 怦 喘 ', '夯 枷 ', '外 勞 ', '臺 灣 人 ', '落 湳 ', '苑 裡 坑 ', '坑 仔 內 ', '起 慼 到 地 ', '雨 晴 ', '紅 蟲 ', '大 湖 ', '誻 誻 叫 ', '柴 球 ', '大 胃 王 ', '大 稻 埕 ', '偷 壘 ', '鬆 餅 ', '喙 罨 囊 ', '龍 文 ', '時 局 ', '摔 死 ', '煞 尾 ', '無 話 講 茭 荖 ', '下 暗 飯 ', '一 籠 ', '一 定 考 袂 牢 ', '看 一 个 影 生 一 个 囝 ', '倒 踅 ', '筆 型 ', '歸 正 修 善 ', '滯 到 ', '變 天 ', '一 工 到 暗 ', '雲 吞 ', '有 幾 項 菜 ', '炎 舞 ', '鹿 角 龜 ', '過 路 線 ', '惡 馬 惡 人 騎 ', '粗 俗 ', '這 个 偌 濟 錢 ', '七 仔 ', '看 甲 凊 凊 楚 楚 ', '戇 神 ', '發 生 ', '病 囡 仔 ', '心 花 當 開 ', '番 鼎 仔 ', '老 硞 硞 ', '大 傢 伙 ', '名 聲 真 敨 ', '攕 烘 肉 ', '滑 ', '龜 蛇 ', '水 雞 皮 仔 ', '攑 硬 篙 ', '抾 無 三 門 墓 著 想 欲 做 土 公 ', '紅 圓 仔 ', '臺 北 橋 ', '雲 林 縣 ', '臺 中 港 ', '水 里 ', '臺 南 市 ', '七 堵 ', '做 功 德 ', '大 村 鄉 ', '小 喇 叭 ', '紹 ', '漢 草 真 好 ', '田 嬰 ', '按 呢 生 ', '海 尾 ', '無 米 閣 拄 著 閏 月 ', '枝 香 小 細 ', '噗 ', '頭 尾 ', '五 短 生 張 ', '正 常 ', '套 牢 咧 ', '動 物 性 膠 質 ', '雪 文 精 ', '悠 遊 卡 ', '你 攏 無 歇 睏 喔 ', '埤 頭 鄉 ', '信 義 大 安 路 口 ', '三 三 八 八 ', '你 話 毋 通 烏 白 講 ', '麥 寮 鄉 ', '你 莫 定 定 挖 肚 臍 ', '新 安 路 ', '金 錢 毋 是 萬 能 的 ', '菠 菱 仔 菜 ', '富 寮 里 ', '你 是 啥 人 ', '反 烏 ', '新 街 ', '合 銅 ', '疼 疼 ', '番 麥 殼 ', '天 氣 冷 矣 你 就 愛 加 疊 一 領 衫 ', '我 到 底 看 著 啥 物 ', '手 扞 仔 ', '姑 不 二 三 將 ', '品 格 ', '透 種 仔 ', '漚 腳 數 ', '隔 音 壁 ', '拍 通 透 ', '開 花 滿 天 芳 結 子 才 驚 人 ', '東 北 季 風 ', '無 人 機 ', '做 牛 無 惜 力 ', '淨 空 排 放 ', '這 藥 仔 抹 落 去 真 緊 就 會 退 癀 矣 ', '毛 蓑 仔 ', '抉 喙 䫌 ', '陽 明 山 ', '咖 啡 館 ', '囡 仔 色 ', '佇 墜 樓 前 一 點 鐘 ', '伊 規 心 欲 考 大 學 ', '東 湖 國 中 ', '中 原 公 園 ', '半 路 店 ', '檳 榔 坑 ', '東 石 鄉 ', '摒 掃 的 ', '無 中 心 化 ', '肉 粽 角 ', '編 譯 器 ', '厝 邊 頭 尾 ', '桃 源 街 ', '仁 愛 杭 州 路 口 ', '千 葉 ', '七 色 圖 ', '大 吉 大 利 ', '尪 仔 頭 鏡 ', '徐 ', '咱 做 代 誌 的 時 陣 ', '包 水 餃 ', '歹 鳥 毋 知 飛 歹 柴 破 袂 開 ', '分 裝 場 ', '健 康 中 心 ', '印 度 尼 西 亞 ', '新 里 族 ', '獅 仔 頭 ', '大 度 路 ', '市 仔 ', '露 營 區 ', '學 姐 ', '枋 南 線 ', '虎 尾 鎮 ', '瀉 腹 肚 ', '恆 春 鎮 ', '小 血 球 ', '破 格 ', '我 衫 攏 穿 上 大 領 ', '溜 落 來 ', '半 條 命 ', '生 活 習 慣 ', '電 影 間 ', '菜 脯 卵 ', '塗 塗 塗 ', '鐵 甲 牛 ', '風 火 頭 ', '現 流 仔 ', '白 了 工 ', '空 港 ', '較 大 ', '公 正 橋 ', '巴 結 ', '果 汁 ', '有 䆀 無 一 好 ', '這 時 ', '竹 北 ', '下 早 ', '較 早 睏 ', '六 六 大 順 ', '公 視 ', '趕 趕 緊 緊 ', '帕 仔 ', '藍 瘦 香 菇 ', '山 貓 ', '大 頭 狗 母 ', '土 板 仁 豆 ', '咧 ', '內 緣 ', '阮 會 曉 唸 ', '茶 末 ', '真 有 喙 水 ', '魔 導 士 ', '先 承 認 你 就 是 恁 朋 友 ', '青 山 王 ', '奧 克 蘭 ', '金 東 ', '便 若 ', '陳 奕 齊 ', '九 尾 金 ', '貓 空 ', '過 tang跤 ', '頭 汴 坑 溪 ', '無 定 著 ', '控 機 仔 ', '趨 湧 ', '中 洲 ', '青 田 街 ', '同 房 ', '鼢 底 的 ', '多 元 性 別 ', '舊 厝 ', '貓 潲 ', '福 連 國 小 ', '點 撇 ', '玜 玳 ', '欲 起 鼓 矣 ', '納 豆 ', '中 環 ', '你 死 我 活 ', '踏 著 歹 地 步 ', '曲 去 ', '怙 喙 講 个 無 準 算 ', '交 力 坪 ', '愈 來 愈 嚴 重 ', '一 个 一 个 ', '淡 江 大 橋 ', '上 大 代 死 煞 ', '檨 仔 葉 公 ', '胳 胴 跤 ', '郁 永 河 ', '講 啥 物 芋 仔 番 薯 ', '霓 ', '青 盲 雞 啄 著 蟲 ', '搣 屎 毋 知 臭 ', '斗 南 ', '孤 笑 無 嗣 ', '水 鬼 仔 ', '門 將 ', '手 控 ', '心 胞 膜 炎 ', '敢 食 汽 油 ', '阿 卜 蛇 ', '機 動 戰 士 ', '便 當 ', '敧 一 爿 ', '敲 仙 古 ', '所 羅 門 群 島 ', '終 界 ', '我 愛 台 語 ', '溝 頂 ', '墊 定 ', '詳 解 ', '火 燒 ', '絡 繹 不 ��� ', '尻 川 門 ', '甌 仔 疊 碟 仔 ', '黃 巾 甕 仔 ', '汕 ', '生 甲 袂 䆀 ', '狗 母 酥 ', '倚 桌 仔 ', '中 央 大 學 ', '石 門 水 庫 ', '亂 使 想 ', '百 貨 店 ', '酸 素 矸 ', '蛤 kai', '洗 衫 仔 枋 ', '天 台 ', '數 位 pay', '漚 缺 ', '鈍 市 貨 ', '偷 走 壘 ', '夭 壽 鬼 ', '好 所 在 ', '軟 市 ', '徹 理 ', '現 挽 ', '叫 電 話 ', '伊 生 做 遮 爾 臭 老 ', '魔 神 仔 咒 讖 ', '一 點 點 仔 ', '兩 光 ', '契 查 某 囝 ', '提 著 ', '傷 心 酒 店 ', '過 失 致 死 ', '較 拚 咧 ', '透 身 大 汗 ', '碌 硞 馬 仔 ', '兄 弟 姊 妹 著 愛 仝 心 ', '家 伙 仔 ', '垃 圾 物 仔 ', '狐 狸 貂 ', '石 斑 ', '虎 魚 ', '落 雨 了 後 塗 跤 變 甲 澹 漉 漉 ', '較 慘 ', '基 隆 市 ', '你 欲 行 對 佗 位 去 ', '敦 化 和 平 路 口 ', '港 仔 喙 ', '阮 囝 今 年 二 十 出 頭 矣 ', '新 港 飴 ', '哀 父 叫 母 ', '一 份 ', '毛 毛 仔 雨 ', '磐 安 ', '牛 籠 ', '袂 看 得 ', '立 功 立 德 ', '龜 山 島 ', '過 晝 ', '捒 做 堆 ', '梅 仔 跤 ', '包 帶 ', '番 地 ', '三 重 ', '林 子 口 ', '筆 電 ', '操 刀 ', '揣 轉 來 ', '指 中 指 ', '珠 仔 台 ', '新 廍 ', '相 帶 ', '頂 塊 廖 ', '竹 南 ', '你 共 包 仔 提 去 熁 燒 一 下 ', '平 方 根 ', '頂 公 館 ', '散 仙 ', '演 藝 界 ', '繪 本 ', '毋 情 毋 願 ', '較 緊 ', '有 也 好 無 也 好 ', '操 心 ', '摃 槌 仔 龍 ', '怪 奇 古 ', '國 破 家 亡 ', '新 羅 ', '貴 氣 ', '沓 沓 仔 ', '拍 薄 ', '物 件 若 予 伊 提 過 手 ', '輾 仔 鞋 ', '異 界 ', '鼠 尾 風 ', '湖 內 ', '提 走 ', '無 打 無 啥 ', '我 欲 準 備 落 山 矣 ', '盜 用 ', '聽 無 ', '彼 个 頭 家 娘 對 人 客 誠 好 禮 ', '大 細 輦 ', '無 歇 ', '無 疑 悟 你 會 出 國 讀 冊 ', '石 園 ', '嘉 義 ', '後 寮 ', '我 攏 有 看 著 ', '劍 南 路 ', '歹 天 ', '三 跤 步 一 坎 店 ', '臘 肉 ', '舊 里 族 ', '下 晡 點 心 ', '冷 管 ', '無 及 格 ', '公 允 ', '十 喙 九 尻 川 ', '投 影 片 ', '納 錢 ', '墓 坑 鳥 ', '活 餌 桶 仔 ', '激 屎 面 ', '袂 對 同 ', '紡 織 機 ', '木 質 部 ', '落 口 講 出 來 ', '投 丁 ', '棚 頂 做 甲 流 汗 棚 跤 嫌 甲 流 瀾 ', '僫 鬥 陣 ', '拍 死 板 ', '捅 鼻 ', '搭 峇 ', '簡 述 ', '一 个 接 一 个 ', '緊 來 旋 ', '閒 仔 話 ', '拍 爽 ', '德 拉 瓦 ', '總 舖 ', '三 日 不 見 久 溜 溜 ', '合 掛 ', '手 神 重 ', '電 子 ', '暗 空 ', '瘦 食 ', '塑 膠 車 ', '要 意 ', '燒 雞 胿 ', '吊 猴 ', '掠 猴 ', '暗 頭 仔 ', '濟 囝 濟 擘 腹 濟 新 婦 濟 體 剔 ', '交 球 ', '無 拄 好 ', '搶 頭 標 ', '金 環 失 日 ', '觀 音 大 士 ', '在 準 ', '欲 暗 矣 ', '嘔 落 ', '蛣 蛚 ', '一 目 仔 ', '提 款 片 ', '無 你 个 代 ', '天 公 祖 ', '串 講 ', '離 題 ', '馬 鈴 薯 條 ', '做 塗 水 的 ', '人 情 味 ', '劉 銘 傳 ', '肝 包 油 ', '糖 醋 ', '二 戰 ', '拍 鐵 師 ', '慢 一 跤 步 ', '提 批 的 ', '下 禮 拜 ', '死 亡 之 握 ', '你 毋 通 囥 佇 心 肝 內 ', '臭 龜 仔 ', '趁 一 空 食 三 冬 ', '我 欲 學 臺 語 ', '埋 ', '馬 卡 道 ', '箍 喙 罨 ', '貴 州 省 ', '敦 化 北 路 ', '你 看 起 來 是 遮 爾 仔 媠 ', '精 个 食 戇 戇 个 食 天 公 ', '轉 去 ', '下 晡 市 ', '幾 个 ', '邦 長 ', '港 墘 ', '字 條 仔 ', '無 去 矣 ', '言 行 錄 ', '買 空 ', '六 點 ', '死 忠 ', '石 母 奶 ', '耳 仔 機 ', '貢 寮 區 ', '含 血 噴 天 ', '大 好 額 人 ', '行 政 院 ', '食 市 ', '九 塊 厝 ', '冷 清 ', '月 光 ', '種 喙 齒 ', '街 友 ', '天 公 星 ', '縣 ', '愛 臺 語 ', '我 強 欲 袂 赴 矣 ', '添 飯 ', '有 連 線 ', '昶 ', '中 國 話 ', '攑 香 綴 拜 ', '四 跤 草 ', '疼 風 ', '觀 覽 ', '吉 祥 卵 ', '擲 掉 ', '打 狗 山 ', '西 瓜 倚 大 爿 ', '有 這 款 的 代 誌 我 攏 毋 知 ', '磨 豆 仔 機 ', '國 姓 爺 ', '林 口 區 ', '潘 ', '可 算 名 詞 ', '代 誌 大 碗 ', '半 信 半 疑 ', '恬 稚 恬 稚 討 客 兄 唯 是 ', '遛 光 光 ', '扲 糖 無 洗 手 的 朋 友 ', '烏 日 ', '魏 風 ', '膵 臟 ', '犯 險 ', '連 半 个 人 影 嘛 無 ', '吊 褲 ', '塗 水 工 ', '霧 嗄 嗄 ', '飛 行 船 ', '欲 完 矣 ', '運 將 ', '恁 老 母 拄 咧 念 你 ', '伊 有 誠 濟 內 孫 ', '港 仔 喙 國 小 ', '橐 個 束 個 ', '落 尾 ', '平 枋 電 腦 ', '毛 毛 仔 雨 落 久 塗 塗 嘛 會 澹 ', '冷 滾 水 ', '一 个 紅 龜 按 一 个 位 ', '鹹 酥 雞 ', '雞 卵 糕 仔 ', '溼 汗 ', '諸 島 ', '聖 誕 老 阿 公 ', '天 頂 白 茫 茫 ', '飯 煎 ', '男 權 ', '毋 認 輸 ', '餘 溫 ', '包 山 包 海 ', '踮 空 龜 ', '洗 衫 精 ', '迒 境 電 商 ', '開 喙 蚶 粒 粒 臭 ', '焦 水 期 ', '老 龜 精 ', '塑 膠 橐 仔 ', '蘇 維 埃 聯 盟 ', '臭 水 ', '束 頷 頸 仔 ', '飛 行 機 ', '平 溪 ', '唯 恐 天 下 不 亂 ', '錢 票 ', '瓜 仔 鬚 ', '羊 角 三 劍 ', '半 腰 ', '辭 彙 ', '衝 湧 ', '敢 有 問 題 ', '食 涼 ', '畫 蛇 添 足 ', '做 塗 水 ', '怪 奇 ', '板 金 ', '交 關 ', '海 牙 ', '中 山 路 ', '番 仔 狗 ', '粉 圓 仔 ', '龜 龜 毛 毛 ', '毋 捌 字 看 告 示 ', '表 單 ', '莒 光 號 ', '海 豬 仔 ', '猴 頭 果 ', '翕 新 娘 相 ', '面 書 ', '茶 葉 蛋 ', '花 枝 招 展 ', '食 人 一 口 還 人 一 斗 ', '鐵 彈 ', '東 白 仔 ', '年 兜 ', '佛 心 投 資 者 ', '人 講 綴 人 講 ', '金 剛 戰 士 ', '做 肉 餅 ', '相 駁 喙 ', '鸚 哥 魚 ', '扁 桃 泉 ', '一 筆 錢 ', '果 菜 ', '柑 仔 蜜 醬 ', '一 枝 草 一 點 露 ', '早 時 ', '大 頭 母 人 ', '包 的 ', '頂 禮 拜 ', '尿 苴 仔 ', '人 驚 鬼 鬼 驚 人 ', '無 記 持 症 ', '日 落 山 ', '偏 鄉 ', '拭 塗 跤 ', '袂 死 心 ', '蓋 濟 ', '左 右 鄰 ', '有 聽 著 無 ', '大 圓 埕 ', '斗 籠 仔 本 ', '摃 寇 ', '野 蓮 ', '勥 查 某 ', '暗 頓 食 啥 ', '草 其 略 仔 ', '暢 快 ', '小 包 ', '薄 餅 ', '趒 ', '暖 帽 ', '無 精 彩 ', '內 家 ', '鬍 鬚 ', '燒 仙 草 ', '痀 崙 ', '吳 剛 剉 桂 ', '沙 灘 ', '人 聲 喊 喝 ', '天 公 無 帶 著 ', '望 安 鄉 ', '食 風 ', '分 子 ', '批 車 ', '大 舌 ', '公 館 路 ', '碧 潭 路 ', '臺 北 歐 洲 學 校 小 學 部 ', '充 耳 不 聞 ', '四 份 仔 ', '頭 崁 的 ', '南 機 場 ', '永 綏 街 ', '朴 子 溪 ', '池 上 ', '跤 車 ', '管 待 ', '苦 袂 當 ', '陳 滄 江 ', '缺 囝 化 ', '硨 磲 ', '共 人 唌 ', '頂 塊 黃 ', '潮 州 街 口 ', '社 群 ', '鄉 長 厝 ', '豐 樂 公 園 ', '金 湖 鎮 ', '忠 孝 復 興 ', '民 族 區 運 路 口 ', '松 信 路 ', '糋 麭 粉 ', '鄞 州 ', '台 北 聯 絡 線 ', '又 閣 咧 咳 嗽 ', '伊 加 我 一 輩 ', '霜 仔 ', '魚 池 鄉 ', '囝 甘 仔 囝 ', '四 跤 水 仙 ', '暖 暖 區 ', '用 齒 抿 仔 洗 喙 時 愛 先 捋 齒 膏 ', '新 社 ', '母 身 若 顧 予 伊 好 ', '實 喉 ', '埔 尾 ', '步 路 ', '冰 糖 ', '復 興 橋 ', '阿 拉 ', '繏 絚 ', '員 林 市 ', '蝦 糋 ', '戇 代 誌 ', '年 拄 年 ', '景 興 路 ', '海 結 仔 頭 ', '一 過 半 過 ', '實 聯 制 ', '後 擴 ', '瑞 芳 ', '蘭 嶼 貓 頭 鳥 ', '貓 羅 溪 ', '子 宮 喙 癌 ', '果 子 宅 ', '假 說 ', '不 在 ', '燕 巢 區 ', '上 海 毛 蟹 ', '意 式 麵 ', '捲 風 ', '話 語 之 中 ', '皮 蛋 精 肉 糜 ', '紅 豆 仔 麭 ', '頂 回 ', '相 見 ', '三 兩 人 講 四 斤 話 ', '梘 尾 ', '質 子 ', '兩 箍 ', '真 珠 看 做 鳥 鼠 屎 ', '天 晴 ', '角 運 動 量 ', '莫 問 足 恐 怖 ', '鼻 隔 間 ', '叨 撚 ', '止 疼 藥 ', '恙 蟲 病 ', '火 成 岩 ', '許 崑 源 ', '土 象 ', '豬 頭 癀 ', '禁 喙 ', '昨 昏 ', '卡 通 ', '番 薯 片 ', '砰 去 ', '卵 珠 ', '歡 喜 甘 願 ', '大 海 毋 驚 大 水 ', '橫 的 ', '跤 手 賤 ', '旭 ', '仙 巴 掌 ', '徛 桌 櫃 ', '查 畝 營 ', '番 薯 球 ', '芳 料 草 ', '大 火 ', '夥 計 某 ', '英 國 話 ', '明 知 故 問 ', '老 街 ', '看 有 ', '燃 柴 添 火 著 ', '藝 文 活 動 ', '臺 羅 字 ', '利 ', '金 煌 檨 ', '死 袂 見 笑 ', '嚇 止 ', '加 法 ', '馬 鈴 薯 片 ', '日 頭 曝 尻 川 矣 閣 毋 起 來 ', '英 語 課 本 ', '凍 水 機 ', '大 肚 胿 仔 ', '卑 南 ', '袂 當 干 焦 我 看 著 ', '牛 睏 山 ', '代 誌 好 勢 矣 未 ', '媠 氣 ', '景 文 街 ', '咒 天 咒 地 ', '今 年 是 一 个 好 年 冬 ', '事 假 ', '烏 山 頭 ', '三 講 四 毋 著 ', '語 素 文 字 ', '反 差 ', '大 日 本 帝 國 ', '迒 界 網 商 ', '嚨 喉 ', '褪 躘 ', '莫 假 ', '緊 去 做 代 誌 較 要 緊 ', '你 講 啥 ', '頸 椎 ', '違 扴 ', '身 體 健 康 ', '跤 手 十 足 ', '電 磁 學 ', '繫 年 ', '大 鑼 大 鼓 ', '伊 是 一 个 大 美 人 ', '解 溶 ', '磅 去 ', '你 陪 我 去 彼 爿 好 無 ', '網 路 用 甲 牢 咧 ', '酒 駛 ', '孤 單 一 身 ', '家 治 ', '死 忠 迷 眾 ', '浮 洲 仔 ', '孤 行 獨 市 ', '日 冕 ', '注 目 ', '擉 仔 ', '燒 狗 ', '名 喙 ', '創 辦 人 ', '水 燦 林 ', '飼 奶 動 物 ', '目 睭 擘 金 ', '抾 囡 仔 ', '我 予 滾 水 燙 一 下 膨 疱 足 疼 的 ', '象 桮 ', '有 的 人 ', '瓜 月 ', '三 字 經 ', '飯 焦 ', '天 車 ', '梅 毒 ', '目 仔 久 ', '耙 形 ', '便 物 ', '鹽 酸 草 ', '番 仔 番 薯 ', '每 一 擺 來 你 攏 煮 好 料 的 ', '來 喔 緊 來 看 喔 ', '番 界 ', '總 書 記 ', '破 柴 ', '列 位 ', '鳳 山 ', '劉 厝 ', '凱 旋 武 昌 ', '金 美 國 小 ', '竹 北 市 ', '橋 頭 區 ', '南 州 ', '和 美 鎮 ', '中 壢 ', '西 區 ', '國 泰 ', '水 長 流 ', '中 央 路 ', '南 福 德 ', '金 華 大 廈 ', '獅 甲 ', '士 林 區 ', '紙 票 變 厚 ', '中 山 橋 ', '彰 化 銀 行 ', '黃 國 昌 ', '翠 峰 橋 ', '花 仔 菜 ', '中 正 國 小 ', '按 呢 就 好 ', '老 去 矣 ', '車 埕 ', '南 陽 街 ', '匈 奴 ', '松 壽 路 口 ', '中 坑 ', '不 速 之 客 ', '瑞 源 ', '後 驛 ', '大 稻 埕 ', '鳥 仔 弓 ', '再 敗 ', '新 營 區 ', '正 義 郵 局 ', '寧 夏 路 ', '動 漫 ', '大 和 園 ', '仁 愛 鄉 ', '快 龍 ', '範 ', '西 面 ', '食 鹼 ', '吊 懸 低 ', '先 生 娘 ', '拍 鐵 寮 ', '露 營 區 ', '韻 尾 ', '外 雙 溪 ', '信 義 區 ', '恁 阿 母 敢 知 影 你 佇 遮 發 廢 文 ', '敢 按 呢 ', '厚 操 煩 ', '望 星 橋 ', '姊 夫 ', '十 二 甲 ', '文 昌 橋 ', '有 要 緊 無 ', '林 內 鄉 ', '紅 目 石 獅 ', '囡 仔 人 嘛 看 有 ', '聽 帶 ', '歕 鼓 吹 ', '歹 喙 斗 ', '查 某 營 ', '滷 菜 頭 ', '跳 過 ', '鴨 母 拖 秤 錘 ', '不 貪 不 取 ', '契 兄 ', '白 墨 粉 ', '天 安 門 廣 場 ', '投 文 ', '隱 名 化 ', '粗 花 ', '雞 籠 蜂 ', '暗 眠 摸 山 貓 ', '袂 曉 講 話 ', '搖 床 ', '順 序 ', '捎 攏 無 ', '企 業 家 ', '梯 度 ', '足 久 無 看 見 ', '起 雞 母 皮 ', '台 東 ', '不 見 天 ', '內 華 達 ', '釣 蝦 仔 場 ', '罟 寮 仔 ', '五 支 指 頭 仔 咬 起 來 逐 支 嘛 疼 ', '羊 毛 揻 ', '厝 尾 頂 ', '扞 事 人 ', '大 箍 ', '較 低 ', '客 服 ', '鴨 母 泅 ', '蚵 仔 菇 ', '海 口 ', '阿 里 不 達 ', '反 桌 ', '截 ', '屎 啦 ', '臭 屎 星 ', '摸 王 爺 尻 川 ', '切 腹 ', '雄 三 飛 彈 ', '一 切 攏 是 假 的 ', '小 山 崙 仔 ', '剪 仔 龜 ', '青 盲 仔 目 鏡 ', '親 愛 的 ', '在 地 大 漢 ', '欲 去 佗 位 ', '崁 頭 鴨 ', '冕 旒 ', '跩 著 ', '雞 仔 腸 鳥 仔 肚 ', '門 擋 仔 ', '菱 角 龍 ', '狗 頭 芙 蓉 ', '癱 瘓 ', '我 欲 去 便 所 ', '彼 當 時 ', '鼻 淚 管 ', '代 誌 毋 好 ', '浸 透 ', '瓦 斯 彈 ', '材 料 科 學 ', '甕 底 水 雞 ', '匯 錢 ', '睏 袂 去 ']
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
normalizer.json
ADDED
|
@@ -0,0 +1,1742 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"accessorise": "accessorize",
|
| 3 |
+
"accessorised": "accessorized",
|
| 4 |
+
"accessorises": "accessorizes",
|
| 5 |
+
"accessorising": "accessorizing",
|
| 6 |
+
"acclimatisation": "acclimatization",
|
| 7 |
+
"acclimatise": "acclimatize",
|
| 8 |
+
"acclimatised": "acclimatized",
|
| 9 |
+
"acclimatises": "acclimatizes",
|
| 10 |
+
"acclimatising": "acclimatizing",
|
| 11 |
+
"accoutrements": "accouterments",
|
| 12 |
+
"aeon": "eon",
|
| 13 |
+
"aeons": "eons",
|
| 14 |
+
"aerogramme": "aerogram",
|
| 15 |
+
"aerogrammes": "aerograms",
|
| 16 |
+
"aeroplane": "airplane",
|
| 17 |
+
"aeroplanes": "airplanes",
|
| 18 |
+
"aesthete": "esthete",
|
| 19 |
+
"aesthetes": "esthetes",
|
| 20 |
+
"aesthetic": "esthetic",
|
| 21 |
+
"aesthetically": "esthetically",
|
| 22 |
+
"aesthetics": "esthetics",
|
| 23 |
+
"aetiology": "etiology",
|
| 24 |
+
"ageing": "aging",
|
| 25 |
+
"aggrandisement": "aggrandizement",
|
| 26 |
+
"agonise": "agonize",
|
| 27 |
+
"agonised": "agonized",
|
| 28 |
+
"agonises": "agonizes",
|
| 29 |
+
"agonising": "agonizing",
|
| 30 |
+
"agonisingly": "agonizingly",
|
| 31 |
+
"almanack": "almanac",
|
| 32 |
+
"almanacks": "almanacs",
|
| 33 |
+
"aluminium": "aluminum",
|
| 34 |
+
"amortisable": "amortizable",
|
| 35 |
+
"amortisation": "amortization",
|
| 36 |
+
"amortisations": "amortizations",
|
| 37 |
+
"amortise": "amortize",
|
| 38 |
+
"amortised": "amortized",
|
| 39 |
+
"amortises": "amortizes",
|
| 40 |
+
"amortising": "amortizing",
|
| 41 |
+
"amphitheatre": "amphitheater",
|
| 42 |
+
"amphitheatres": "amphitheaters",
|
| 43 |
+
"anaemia": "anemia",
|
| 44 |
+
"anaemic": "anemic",
|
| 45 |
+
"anaesthesia": "anesthesia",
|
| 46 |
+
"anaesthetic": "anesthetic",
|
| 47 |
+
"anaesthetics": "anesthetics",
|
| 48 |
+
"anaesthetise": "anesthetize",
|
| 49 |
+
"anaesthetised": "anesthetized",
|
| 50 |
+
"anaesthetises": "anesthetizes",
|
| 51 |
+
"anaesthetising": "anesthetizing",
|
| 52 |
+
"anaesthetist": "anesthetist",
|
| 53 |
+
"anaesthetists": "anesthetists",
|
| 54 |
+
"anaesthetize": "anesthetize",
|
| 55 |
+
"anaesthetized": "anesthetized",
|
| 56 |
+
"anaesthetizes": "anesthetizes",
|
| 57 |
+
"anaesthetizing": "anesthetizing",
|
| 58 |
+
"analogue": "analog",
|
| 59 |
+
"analogues": "analogs",
|
| 60 |
+
"analyse": "analyze",
|
| 61 |
+
"analysed": "analyzed",
|
| 62 |
+
"analyses": "analyzes",
|
| 63 |
+
"analysing": "analyzing",
|
| 64 |
+
"anglicise": "anglicize",
|
| 65 |
+
"anglicised": "anglicized",
|
| 66 |
+
"anglicises": "anglicizes",
|
| 67 |
+
"anglicising": "anglicizing",
|
| 68 |
+
"annualised": "annualized",
|
| 69 |
+
"antagonise": "antagonize",
|
| 70 |
+
"antagonised": "antagonized",
|
| 71 |
+
"antagonises": "antagonizes",
|
| 72 |
+
"antagonising": "antagonizing",
|
| 73 |
+
"apologise": "apologize",
|
| 74 |
+
"apologised": "apologized",
|
| 75 |
+
"apologises": "apologizes",
|
| 76 |
+
"apologising": "apologizing",
|
| 77 |
+
"appal": "appall",
|
| 78 |
+
"appals": "appalls",
|
| 79 |
+
"appetiser": "appetizer",
|
| 80 |
+
"appetisers": "appetizers",
|
| 81 |
+
"appetising": "appetizing",
|
| 82 |
+
"appetisingly": "appetizingly",
|
| 83 |
+
"arbour": "arbor",
|
| 84 |
+
"arbours": "arbors",
|
| 85 |
+
"archaeologically": "archeologically",
|
| 86 |
+
"archaeologist": "archeologist",
|
| 87 |
+
"archaeologists": "archeologists",
|
| 88 |
+
"archaeology": "archeology</span>",
|
| 89 |
+
"archeological": "archaeological",
|
| 90 |
+
"ardour": "ardor",
|
| 91 |
+
"armour": "armor",
|
| 92 |
+
"armoured": "armored",
|
| 93 |
+
"armourer": "armorer",
|
| 94 |
+
"armourers": "armorers",
|
| 95 |
+
"armouries": "armories",
|
| 96 |
+
"armoury": "armory",
|
| 97 |
+
"artefact": "artifact",
|
| 98 |
+
"artefacts": "artifacts",
|
| 99 |
+
"authorise": "authorize",
|
| 100 |
+
"authorised": "authorized",
|
| 101 |
+
"authorises": "authorizes",
|
| 102 |
+
"authorising": "authorizing",
|
| 103 |
+
"axe": "ax",
|
| 104 |
+
"backpedalled": "backpedaled",
|
| 105 |
+
"backpedalling": "backpedaling",
|
| 106 |
+
"bannister": "banister",
|
| 107 |
+
"bannisters": "banisters",
|
| 108 |
+
"baptise": "baptize",
|
| 109 |
+
"baptised": "baptized",
|
| 110 |
+
"baptises": "baptizes",
|
| 111 |
+
"baptising": "baptizing",
|
| 112 |
+
"bastardise": "bastardize",
|
| 113 |
+
"bastardised": "bastardized",
|
| 114 |
+
"bastardises": "bastardizes",
|
| 115 |
+
"bastardising": "bastardizing",
|
| 116 |
+
"battleax": "battleaxe",
|
| 117 |
+
"baulk": "balk",
|
| 118 |
+
"baulked": "balked",
|
| 119 |
+
"baulking": "balking",
|
| 120 |
+
"baulks": "balks",
|
| 121 |
+
"bedevilled": "bedeviled",
|
| 122 |
+
"bedevilling": "bedeviling",
|
| 123 |
+
"behaviour": "behavior",
|
| 124 |
+
"behavioural": "behavioral",
|
| 125 |
+
"behaviourism": "behaviorism",
|
| 126 |
+
"behaviourist": "behaviorist",
|
| 127 |
+
"behaviourists": "behaviorists",
|
| 128 |
+
"behaviours": "behaviors",
|
| 129 |
+
"behove": "behoove",
|
| 130 |
+
"behoved": "behooved",
|
| 131 |
+
"behoves": "behooves",
|
| 132 |
+
"bejewelled": "bejeweled",
|
| 133 |
+
"belabour": "belabor",
|
| 134 |
+
"belaboured": "belabored",
|
| 135 |
+
"belabouring": "belaboring",
|
| 136 |
+
"belabours": "belabors",
|
| 137 |
+
"bevelled": "beveled",
|
| 138 |
+
"bevvies": "bevies",
|
| 139 |
+
"bevvy": "bevy",
|
| 140 |
+
"biassed": "biased",
|
| 141 |
+
"biassing": "biasing",
|
| 142 |
+
"bingeing": "binging",
|
| 143 |
+
"bougainvillaea": "bougainvillea",
|
| 144 |
+
"bougainvillaeas": "bougainvilleas",
|
| 145 |
+
"bowdlerise": "bowdlerize",
|
| 146 |
+
"bowdlerised": "bowdlerized",
|
| 147 |
+
"bowdlerises": "bowdlerizes",
|
| 148 |
+
"bowdlerising": "bowdlerizing",
|
| 149 |
+
"breathalyse": "breathalyze",
|
| 150 |
+
"breathalysed": "breathalyzed",
|
| 151 |
+
"breathalyser": "breathalyzer",
|
| 152 |
+
"breathalysers": "breathalyzers",
|
| 153 |
+
"breathalyses": "breathalyzes",
|
| 154 |
+
"breathalysing": "breathalyzing",
|
| 155 |
+
"brutalise": "brutalize",
|
| 156 |
+
"brutalised": "brutalized",
|
| 157 |
+
"brutalises": "brutalizes",
|
| 158 |
+
"brutalising": "brutalizing",
|
| 159 |
+
"busses": "buses",
|
| 160 |
+
"bussing": "busing",
|
| 161 |
+
"caesarean": "cesarean",
|
| 162 |
+
"caesareans": "cesareans",
|
| 163 |
+
"calibre": "caliber",
|
| 164 |
+
"calibres": "calibers",
|
| 165 |
+
"calliper": "caliper",
|
| 166 |
+
"callipers": "calipers",
|
| 167 |
+
"callisthenics": "calisthenics",
|
| 168 |
+
"canalise": "canalize",
|
| 169 |
+
"canalised": "canalized",
|
| 170 |
+
"canalises": "canalizes",
|
| 171 |
+
"canalising": "canalizing",
|
| 172 |
+
"cancelation": "cancellation",
|
| 173 |
+
"cancelations": "cancellations",
|
| 174 |
+
"cancelled": "canceled",
|
| 175 |
+
"cancelling": "canceling",
|
| 176 |
+
"candour": "candor",
|
| 177 |
+
"cannibalise": "cannibalize",
|
| 178 |
+
"cannibalised": "cannibalized",
|
| 179 |
+
"cannibalises": "cannibalizes",
|
| 180 |
+
"cannibalising": "cannibalizing",
|
| 181 |
+
"canonise": "canonize",
|
| 182 |
+
"canonised": "canonized",
|
| 183 |
+
"canonises": "canonizes",
|
| 184 |
+
"canonising": "canonizing",
|
| 185 |
+
"capitalise": "capitalize",
|
| 186 |
+
"capitalised": "capitalized",
|
| 187 |
+
"capitalises": "capitalizes",
|
| 188 |
+
"capitalising": "capitalizing",
|
| 189 |
+
"caramelise": "caramelize",
|
| 190 |
+
"caramelised": "caramelized",
|
| 191 |
+
"caramelises": "caramelizes",
|
| 192 |
+
"caramelising": "caramelizing",
|
| 193 |
+
"carbonise": "carbonize",
|
| 194 |
+
"carbonised": "carbonized",
|
| 195 |
+
"carbonises": "carbonizes",
|
| 196 |
+
"carbonising": "carbonizing",
|
| 197 |
+
"carolled": "caroled",
|
| 198 |
+
"carolling": "caroling",
|
| 199 |
+
"catalogue": "catalog",
|
| 200 |
+
"catalogued": "cataloged",
|
| 201 |
+
"catalogues": "catalogs",
|
| 202 |
+
"cataloguing": "cataloging",
|
| 203 |
+
"catalyse": "catalyze",
|
| 204 |
+
"catalysed": "catalyzed",
|
| 205 |
+
"catalyses": "catalyzes",
|
| 206 |
+
"catalysing": "catalyzing",
|
| 207 |
+
"categorise": "categorize",
|
| 208 |
+
"categorised": "categorized",
|
| 209 |
+
"categorises": "categorizes",
|
| 210 |
+
"categorising": "categorizing",
|
| 211 |
+
"cauterise": "cauterize",
|
| 212 |
+
"cauterised": "cauterized",
|
| 213 |
+
"cauterises": "cauterizes",
|
| 214 |
+
"cauterising": "cauterizing",
|
| 215 |
+
"cavilled": "caviled",
|
| 216 |
+
"cavilling": "caviling",
|
| 217 |
+
"centigramme": "centigram",
|
| 218 |
+
"centigrammes": "centigrams",
|
| 219 |
+
"centilitre": "centiliter",
|
| 220 |
+
"centilitres": "centiliters",
|
| 221 |
+
"centimetre": "centimeter",
|
| 222 |
+
"centimetres": "centimeters",
|
| 223 |
+
"centralise": "centralize",
|
| 224 |
+
"centralised": "centralized",
|
| 225 |
+
"centralises": "centralizes",
|
| 226 |
+
"centralising": "centralizing",
|
| 227 |
+
"centre": "center",
|
| 228 |
+
"centred": "centered",
|
| 229 |
+
"centrefold": "centerfold",
|
| 230 |
+
"centrefolds": "centerfolds",
|
| 231 |
+
"centrepiece": "centerpiece",
|
| 232 |
+
"centrepieces": "centerpieces",
|
| 233 |
+
"centres": "centers",
|
| 234 |
+
"channelled": "channeled",
|
| 235 |
+
"channelling": "channeling",
|
| 236 |
+
"characterise": "characterize",
|
| 237 |
+
"characterised": "characterized",
|
| 238 |
+
"characterises": "characterizes",
|
| 239 |
+
"characterising": "characterizing",
|
| 240 |
+
"cheque": "check",
|
| 241 |
+
"chequebook": "checkbook",
|
| 242 |
+
"chequebooks": "checkbooks",
|
| 243 |
+
"chequered": "checkered",
|
| 244 |
+
"cheques": "checks",
|
| 245 |
+
"chilli": "chili",
|
| 246 |
+
"chimaera": "chimera",
|
| 247 |
+
"chimaeras": "chimeras",
|
| 248 |
+
"chiselled": "chiseled",
|
| 249 |
+
"chiselling": "chiseling",
|
| 250 |
+
"circularise": "circularize",
|
| 251 |
+
"circularised": "circularized",
|
| 252 |
+
"circularises": "circularizes",
|
| 253 |
+
"circularising": "circularizing",
|
| 254 |
+
"civilise": "civilize",
|
| 255 |
+
"civilised": "civilized",
|
| 256 |
+
"civilises": "civilizes",
|
| 257 |
+
"civilising": "civilizing",
|
| 258 |
+
"clamour": "clamor",
|
| 259 |
+
"clamoured": "clamored",
|
| 260 |
+
"clamouring": "clamoring",
|
| 261 |
+
"clamours": "clamors",
|
| 262 |
+
"clangour": "clangor",
|
| 263 |
+
"clarinettist": "clarinetist",
|
| 264 |
+
"clarinettists": "clarinetists",
|
| 265 |
+
"collectivise": "collectivize",
|
| 266 |
+
"collectivised": "collectivized",
|
| 267 |
+
"collectivises": "collectivizes",
|
| 268 |
+
"collectivising": "collectivizing",
|
| 269 |
+
"colonisation": "colonization",
|
| 270 |
+
"colonise": "colonize",
|
| 271 |
+
"colonised": "colonized",
|
| 272 |
+
"coloniser": "colonizer",
|
| 273 |
+
"colonisers": "colonizers",
|
| 274 |
+
"colonises": "colonizes",
|
| 275 |
+
"colonising": "colonizing",
|
| 276 |
+
"colour": "color",
|
| 277 |
+
"colourant": "colorant",
|
| 278 |
+
"colourants": "colorants",
|
| 279 |
+
"coloured": "colored",
|
| 280 |
+
"coloureds": "coloreds",
|
| 281 |
+
"colourful": "colorful",
|
| 282 |
+
"colourfully": "colorfully",
|
| 283 |
+
"colouring": "coloring",
|
| 284 |
+
"colourize": "colorize",
|
| 285 |
+
"colourized": "colorized",
|
| 286 |
+
"colourizes": "colorizes",
|
| 287 |
+
"colourizing": "colorizing",
|
| 288 |
+
"colourless": "colorless",
|
| 289 |
+
"colours": "colors",
|
| 290 |
+
"commercialise": "commercialize",
|
| 291 |
+
"commercialised": "commercialized",
|
| 292 |
+
"commercialises": "commercializes",
|
| 293 |
+
"commercialising": "commercializing",
|
| 294 |
+
"compartmentalise": "compartmentalize",
|
| 295 |
+
"compartmentalised": "compartmentalized",
|
| 296 |
+
"compartmentalises": "compartmentalizes",
|
| 297 |
+
"compartmentalising": "compartmentalizing",
|
| 298 |
+
"computerise": "computerize",
|
| 299 |
+
"computerised": "computerized",
|
| 300 |
+
"computerises": "computerizes",
|
| 301 |
+
"computerising": "computerizing",
|
| 302 |
+
"conceptualise": "conceptualize",
|
| 303 |
+
"conceptualised": "conceptualized",
|
| 304 |
+
"conceptualises": "conceptualizes",
|
| 305 |
+
"conceptualising": "conceptualizing",
|
| 306 |
+
"connexion": "connection",
|
| 307 |
+
"connexions": "connections",
|
| 308 |
+
"contextualise": "contextualize",
|
| 309 |
+
"contextualised": "contextualized",
|
| 310 |
+
"contextualises": "contextualizes",
|
| 311 |
+
"contextualising": "contextualizing",
|
| 312 |
+
"cosier": "cozier",
|
| 313 |
+
"cosies": "cozies",
|
| 314 |
+
"cosiest": "coziest",
|
| 315 |
+
"cosily": "cozily",
|
| 316 |
+
"cosiness": "coziness",
|
| 317 |
+
"cosy": "cozy",
|
| 318 |
+
"councillor": "councilor",
|
| 319 |
+
"councillors": "councilors",
|
| 320 |
+
"counselled": "counseled",
|
| 321 |
+
"counselling": "counseling",
|
| 322 |
+
"counsellor": "counselor",
|
| 323 |
+
"counsellors": "counselors",
|
| 324 |
+
"crenelated": "crenellated",
|
| 325 |
+
"criminalise": "criminalize",
|
| 326 |
+
"criminalised": "criminalized",
|
| 327 |
+
"criminalises": "criminalizes",
|
| 328 |
+
"criminalising": "criminalizing",
|
| 329 |
+
"criticise": "criticize",
|
| 330 |
+
"criticised": "criticized",
|
| 331 |
+
"criticises": "criticizes",
|
| 332 |
+
"criticising": "criticizing",
|
| 333 |
+
"crueller": "crueler",
|
| 334 |
+
"cruellest": "cruelest",
|
| 335 |
+
"crystallisation": "crystallization",
|
| 336 |
+
"crystallise": "crystallize",
|
| 337 |
+
"crystallised": "crystallized",
|
| 338 |
+
"crystallises": "crystallizes",
|
| 339 |
+
"crystallising": "crystallizing",
|
| 340 |
+
"cudgelled": "cudgeled",
|
| 341 |
+
"cudgelling": "cudgeling",
|
| 342 |
+
"customise": "customize",
|
| 343 |
+
"customised": "customized",
|
| 344 |
+
"customises": "customizes",
|
| 345 |
+
"customising": "customizing",
|
| 346 |
+
"cypher": "cipher",
|
| 347 |
+
"cyphers": "ciphers",
|
| 348 |
+
"decentralisation": "decentralization",
|
| 349 |
+
"decentralise": "decentralize",
|
| 350 |
+
"decentralised": "decentralized",
|
| 351 |
+
"decentralises": "decentralizes",
|
| 352 |
+
"decentralising": "decentralizing",
|
| 353 |
+
"decriminalisation": "decriminalization",
|
| 354 |
+
"decriminalise": "decriminalize",
|
| 355 |
+
"decriminalised": "decriminalized",
|
| 356 |
+
"decriminalises": "decriminalizes",
|
| 357 |
+
"decriminalising": "decriminalizing",
|
| 358 |
+
"defence": "defense",
|
| 359 |
+
"defenceless": "defenseless",
|
| 360 |
+
"defences": "defenses",
|
| 361 |
+
"dehumanisation": "dehumanization",
|
| 362 |
+
"dehumanise": "dehumanize",
|
| 363 |
+
"dehumanised": "dehumanized",
|
| 364 |
+
"dehumanises": "dehumanizes",
|
| 365 |
+
"dehumanising": "dehumanizing",
|
| 366 |
+
"demeanour": "demeanor",
|
| 367 |
+
"demilitarisation": "demilitarization",
|
| 368 |
+
"demilitarise": "demilitarize",
|
| 369 |
+
"demilitarised": "demilitarized",
|
| 370 |
+
"demilitarises": "demilitarizes",
|
| 371 |
+
"demilitarising": "demilitarizing",
|
| 372 |
+
"demobilisation": "demobilization",
|
| 373 |
+
"demobilise": "demobilize",
|
| 374 |
+
"demobilised": "demobilized",
|
| 375 |
+
"demobilises": "demobilizes",
|
| 376 |
+
"demobilising": "demobilizing",
|
| 377 |
+
"democratisation": "democratization",
|
| 378 |
+
"democratise": "democratize",
|
| 379 |
+
"democratised": "democratized",
|
| 380 |
+
"democratises": "democratizes",
|
| 381 |
+
"democratising": "democratizing",
|
| 382 |
+
"demonise": "demonize",
|
| 383 |
+
"demonised": "demonized",
|
| 384 |
+
"demonises": "demonizes",
|
| 385 |
+
"demonising": "demonizing",
|
| 386 |
+
"demoralisation": "demoralization",
|
| 387 |
+
"demoralise": "demoralize",
|
| 388 |
+
"demoralised": "demoralized",
|
| 389 |
+
"demoralises": "demoralizes",
|
| 390 |
+
"demoralising": "demoralizing",
|
| 391 |
+
"denationalisation": "denationalization",
|
| 392 |
+
"denationalise": "denationalize",
|
| 393 |
+
"denationalised": "denationalized",
|
| 394 |
+
"denationalises": "denationalizes",
|
| 395 |
+
"denationalising": "denationalizing",
|
| 396 |
+
"deodorise": "deodorize",
|
| 397 |
+
"deodorised": "deodorized",
|
| 398 |
+
"deodorises": "deodorizes",
|
| 399 |
+
"deodorising": "deodorizing",
|
| 400 |
+
"depersonalise": "depersonalize",
|
| 401 |
+
"depersonalised": "depersonalized",
|
| 402 |
+
"depersonalises": "depersonalizes",
|
| 403 |
+
"depersonalising": "depersonalizing",
|
| 404 |
+
"deputise": "deputize",
|
| 405 |
+
"deputised": "deputized",
|
| 406 |
+
"deputises": "deputizes",
|
| 407 |
+
"deputising": "deputizing",
|
| 408 |
+
"desensitisation": "desensitization",
|
| 409 |
+
"desensitise": "desensitize",
|
| 410 |
+
"desensitised": "desensitized",
|
| 411 |
+
"desensitises": "desensitizes",
|
| 412 |
+
"desensitising": "desensitizing",
|
| 413 |
+
"destabilisation": "destabilization",
|
| 414 |
+
"destabilise": "destabilize",
|
| 415 |
+
"destabilised": "destabilized",
|
| 416 |
+
"destabilises": "destabilizes",
|
| 417 |
+
"destabilising": "destabilizing",
|
| 418 |
+
"dialled": "dialed",
|
| 419 |
+
"dialling": "dialing",
|
| 420 |
+
"dialogue": "dialog",
|
| 421 |
+
"dialogues": "dialogs",
|
| 422 |
+
"diarrhoea": "diarrhea",
|
| 423 |
+
"digitise": "digitize",
|
| 424 |
+
"digitised": "digitized",
|
| 425 |
+
"digitises": "digitizes",
|
| 426 |
+
"digitising": "digitizing",
|
| 427 |
+
"disc": "disk",
|
| 428 |
+
"discolour": "discolor",
|
| 429 |
+
"discoloured": "discolored",
|
| 430 |
+
"discolouring": "discoloring",
|
| 431 |
+
"discolours": "discolors",
|
| 432 |
+
"discs": "disks",
|
| 433 |
+
"disembowelled": "disemboweled",
|
| 434 |
+
"disembowelling": "disemboweling",
|
| 435 |
+
"disfavour": "disfavor",
|
| 436 |
+
"dishevelled": "disheveled",
|
| 437 |
+
"dishonour": "dishonor",
|
| 438 |
+
"dishonourable": "dishonorable",
|
| 439 |
+
"dishonourably": "dishonorably",
|
| 440 |
+
"dishonoured": "dishonored",
|
| 441 |
+
"dishonouring": "dishonoring",
|
| 442 |
+
"dishonours": "dishonors",
|
| 443 |
+
"disorganisation": "disorganization",
|
| 444 |
+
"disorganised": "disorganized",
|
| 445 |
+
"distil": "distill",
|
| 446 |
+
"distils": "distills",
|
| 447 |
+
"dramatisation": "dramatization",
|
| 448 |
+
"dramatisations": "dramatizations",
|
| 449 |
+
"dramatise": "dramatize",
|
| 450 |
+
"dramatised": "dramatized",
|
| 451 |
+
"dramatises": "dramatizes",
|
| 452 |
+
"dramatising": "dramatizing",
|
| 453 |
+
"draught": "draft",
|
| 454 |
+
"draughtboard": "draftboard",
|
| 455 |
+
"draughtboards": "draftboards",
|
| 456 |
+
"draughtier": "draftier",
|
| 457 |
+
"draughtiest": "draftiest",
|
| 458 |
+
"draughts": "drafts",
|
| 459 |
+
"draughtsman": "draftsman",
|
| 460 |
+
"draughtsmanship": "draftsmanship",
|
| 461 |
+
"draughtsmen": "draftsmen",
|
| 462 |
+
"draughtswoman": "draftswoman",
|
| 463 |
+
"draughtswomen": "draftswomen",
|
| 464 |
+
"draughty": "drafty",
|
| 465 |
+
"drivelled": "driveled",
|
| 466 |
+
"drivelling": "driveling",
|
| 467 |
+
"duelled": "dueled",
|
| 468 |
+
"duelling": "dueling",
|
| 469 |
+
"economise": "economize",
|
| 470 |
+
"economised": "economized",
|
| 471 |
+
"economises": "economizes",
|
| 472 |
+
"economising": "economizing",
|
| 473 |
+
"editorialise": "editorialize",
|
| 474 |
+
"editorialised": "editorialized",
|
| 475 |
+
"editorialises": "editorializes",
|
| 476 |
+
"editorialising": "editorializing",
|
| 477 |
+
"edoema": "edema",
|
| 478 |
+
"empathise": "empathize",
|
| 479 |
+
"empathised": "empathized",
|
| 480 |
+
"empathises": "empathizes",
|
| 481 |
+
"empathising": "empathizing",
|
| 482 |
+
"emphasise": "emphasize",
|
| 483 |
+
"emphasised": "emphasized",
|
| 484 |
+
"emphasises": "emphasizes",
|
| 485 |
+
"emphasising": "emphasizing",
|
| 486 |
+
"enamelled": "enameled",
|
| 487 |
+
"enamelling": "enameling",
|
| 488 |
+
"enamoured": "enamored",
|
| 489 |
+
"encyclopaedia": "encyclopedia",
|
| 490 |
+
"encyclopaedias": "encyclopedias",
|
| 491 |
+
"encyclopaedic": "encyclopedic",
|
| 492 |
+
"endeavour": "endeavor",
|
| 493 |
+
"endeavoured": "endeavored",
|
| 494 |
+
"endeavouring": "endeavoring",
|
| 495 |
+
"endeavours": "endeavors",
|
| 496 |
+
"energise": "energize",
|
| 497 |
+
"energised": "energized",
|
| 498 |
+
"energises": "energizes",
|
| 499 |
+
"energising": "energizing",
|
| 500 |
+
"enrol": "enroll",
|
| 501 |
+
"enrols": "enrolls",
|
| 502 |
+
"enthral": "enthrall",
|
| 503 |
+
"enthrals": "enthralls",
|
| 504 |
+
"epaulette": "epaulet",
|
| 505 |
+
"epaulettes": "epaulets",
|
| 506 |
+
"epicentre": "epicenter",
|
| 507 |
+
"epicentres": "epicenters",
|
| 508 |
+
"epilogue": "epilog",
|
| 509 |
+
"epilogues": "epilogs",
|
| 510 |
+
"epitomise": "epitomize",
|
| 511 |
+
"epitomised": "epitomized",
|
| 512 |
+
"epitomises": "epitomizes",
|
| 513 |
+
"epitomising": "epitomizing",
|
| 514 |
+
"equalisation": "equalization",
|
| 515 |
+
"equalise": "equalize",
|
| 516 |
+
"equalised": "equalized",
|
| 517 |
+
"equaliser": "equalizer",
|
| 518 |
+
"equalisers": "equalizers",
|
| 519 |
+
"equalises": "equalizes",
|
| 520 |
+
"equalising": "equalizing",
|
| 521 |
+
"eulogise": "eulogize",
|
| 522 |
+
"eulogised": "eulogized",
|
| 523 |
+
"eulogises": "eulogizes",
|
| 524 |
+
"eulogising": "eulogizing",
|
| 525 |
+
"evangelise": "evangelize",
|
| 526 |
+
"evangelised": "evangelized",
|
| 527 |
+
"evangelises": "evangelizes",
|
| 528 |
+
"evangelising": "evangelizing",
|
| 529 |
+
"exorcise": "exorcize",
|
| 530 |
+
"exorcised": "exorcized",
|
| 531 |
+
"exorcises": "exorcizes",
|
| 532 |
+
"exorcising": "exorcizing",
|
| 533 |
+
"extemporisation": "extemporization",
|
| 534 |
+
"extemporise": "extemporize",
|
| 535 |
+
"extemporised": "extemporized",
|
| 536 |
+
"extemporises": "extemporizes",
|
| 537 |
+
"extemporising": "extemporizing",
|
| 538 |
+
"externalisation": "externalization",
|
| 539 |
+
"externalisations": "externalizations",
|
| 540 |
+
"externalise": "externalize",
|
| 541 |
+
"externalised": "externalized",
|
| 542 |
+
"externalises": "externalizes",
|
| 543 |
+
"externalising": "externalizing",
|
| 544 |
+
"factorise": "factorize",
|
| 545 |
+
"factorised": "factorized",
|
| 546 |
+
"factorises": "factorizes",
|
| 547 |
+
"factorising": "factorizing",
|
| 548 |
+
"faecal": "fecal",
|
| 549 |
+
"faeces": "feces",
|
| 550 |
+
"familiarisation": "familiarization",
|
| 551 |
+
"familiarise": "familiarize",
|
| 552 |
+
"familiarised": "familiarized",
|
| 553 |
+
"familiarises": "familiarizes",
|
| 554 |
+
"familiarising": "familiarizing",
|
| 555 |
+
"fantasise": "fantasize",
|
| 556 |
+
"fantasised": "fantasized",
|
| 557 |
+
"fantasises": "fantasizes",
|
| 558 |
+
"fantasising": "fantasizing",
|
| 559 |
+
"favour": "favor",
|
| 560 |
+
"favourable": "favorable",
|
| 561 |
+
"favourably": "favorably",
|
| 562 |
+
"favoured": "favored",
|
| 563 |
+
"favouring": "favoring",
|
| 564 |
+
"favourite": "favorite",
|
| 565 |
+
"favourites": "favorites",
|
| 566 |
+
"favouritism": "favoritism",
|
| 567 |
+
"favours": "favors",
|
| 568 |
+
"feminise": "feminize",
|
| 569 |
+
"feminised": "feminized",
|
| 570 |
+
"feminises": "feminizes",
|
| 571 |
+
"feminising": "feminizing",
|
| 572 |
+
"fertilisation": "fertilization",
|
| 573 |
+
"fertilise": "fertilize",
|
| 574 |
+
"fertilised": "fertilized",
|
| 575 |
+
"fertiliser": "fertilizer",
|
| 576 |
+
"fertilisers": "fertilizers",
|
| 577 |
+
"fertilises": "fertilizes",
|
| 578 |
+
"fertilising": "fertilizing",
|
| 579 |
+
"fervour": "fervor",
|
| 580 |
+
"fibre": "fiber",
|
| 581 |
+
"fibreglass": "fiberglass",
|
| 582 |
+
"fibres": "fibers",
|
| 583 |
+
"fictionalisation": "fictionalization",
|
| 584 |
+
"fictionalisations": "fictionalizations",
|
| 585 |
+
"fictionalise": "fictionalize",
|
| 586 |
+
"fictionalised": "fictionalized",
|
| 587 |
+
"fictionalises": "fictionalizes",
|
| 588 |
+
"fictionalising": "fictionalizing",
|
| 589 |
+
"fillet": "filet",
|
| 590 |
+
"filleted": "fileted",
|
| 591 |
+
"filleting": "fileting",
|
| 592 |
+
"fillets": "filets",
|
| 593 |
+
"finalisation": "finalization",
|
| 594 |
+
"finalise": "finalize",
|
| 595 |
+
"finalised": "finalized",
|
| 596 |
+
"finalises": "finalizes",
|
| 597 |
+
"finalising": "finalizing",
|
| 598 |
+
"flautist": "flutist",
|
| 599 |
+
"flautists": "flutists",
|
| 600 |
+
"flavour": "flavor",
|
| 601 |
+
"flavoured": "flavored",
|
| 602 |
+
"flavouring": "flavoring",
|
| 603 |
+
"flavourings": "flavorings",
|
| 604 |
+
"flavourless": "flavorless",
|
| 605 |
+
"flavours": "flavors",
|
| 606 |
+
"flavoursome": "flavorsome",
|
| 607 |
+
"flyer / flier": "flier / flyer",
|
| 608 |
+
"foetal": "fetal",
|
| 609 |
+
"foetid": "fetid",
|
| 610 |
+
"foetus": "fetus",
|
| 611 |
+
"foetuses": "fetuses",
|
| 612 |
+
"formalisation": "formalization",
|
| 613 |
+
"formalise": "formalize",
|
| 614 |
+
"formalised": "formalized",
|
| 615 |
+
"formalises": "formalizes",
|
| 616 |
+
"formalising": "formalizing",
|
| 617 |
+
"fossilisation": "fossilization",
|
| 618 |
+
"fossilise": "fossilize",
|
| 619 |
+
"fossilised": "fossilized",
|
| 620 |
+
"fossilises": "fossilizes",
|
| 621 |
+
"fossilising": "fossilizing",
|
| 622 |
+
"fraternisation": "fraternization",
|
| 623 |
+
"fraternise": "fraternize",
|
| 624 |
+
"fraternised": "fraternized",
|
| 625 |
+
"fraternises": "fraternizes",
|
| 626 |
+
"fraternising": "fraternizing",
|
| 627 |
+
"fulfil": "fulfill",
|
| 628 |
+
"fulfilment": "fulfillment",
|
| 629 |
+
"fulfils": "fulfills",
|
| 630 |
+
"funnelled": "funneled",
|
| 631 |
+
"funnelling": "funneling",
|
| 632 |
+
"gage": "gauge",
|
| 633 |
+
"gaged": "gauged",
|
| 634 |
+
"gages": "gauges",
|
| 635 |
+
"gaging": "gauging",
|
| 636 |
+
"galvanise": "galvanize",
|
| 637 |
+
"galvanised": "galvanized",
|
| 638 |
+
"galvanises": "galvanizes",
|
| 639 |
+
"galvanising": "galvanizing",
|
| 640 |
+
"gambolled": "gamboled",
|
| 641 |
+
"gambolling": "gamboling",
|
| 642 |
+
"gaol": "jail",
|
| 643 |
+
"gaolbird": "jailbird",
|
| 644 |
+
"gaolbirds": "jailbirds",
|
| 645 |
+
"gaolbreak": "jailbreak",
|
| 646 |
+
"gaolbreaks": "jailbreaks",
|
| 647 |
+
"gaoled": "jailed",
|
| 648 |
+
"gaoler": "jailer",
|
| 649 |
+
"gaolers": "jailers",
|
| 650 |
+
"gaoling": "jailing",
|
| 651 |
+
"gaols": "jails",
|
| 652 |
+
"gasses": "gases",
|
| 653 |
+
"generalisation": "generalization",
|
| 654 |
+
"generalisations": "generalizations",
|
| 655 |
+
"generalise": "generalize",
|
| 656 |
+
"generalised": "generalized",
|
| 657 |
+
"generalises": "generalizes",
|
| 658 |
+
"generalising": "generalizing",
|
| 659 |
+
"ghettoise": "ghettoize",
|
| 660 |
+
"ghettoised": "ghettoized",
|
| 661 |
+
"ghettoises": "ghettoizes",
|
| 662 |
+
"ghettoising": "ghettoizing",
|
| 663 |
+
"gipsies": "gypsies",
|
| 664 |
+
"glamor": "glamour",
|
| 665 |
+
"glamorise": "glamorize",
|
| 666 |
+
"glamorised": "glamorized",
|
| 667 |
+
"glamorises": "glamorizes",
|
| 668 |
+
"glamorising": "glamorizing",
|
| 669 |
+
"globalisation": "globalization",
|
| 670 |
+
"globalise": "globalize",
|
| 671 |
+
"globalised": "globalized",
|
| 672 |
+
"globalises": "globalizes",
|
| 673 |
+
"globalising": "globalizing",
|
| 674 |
+
"glueing": "gluing",
|
| 675 |
+
"goitre": "goiter",
|
| 676 |
+
"goitres": "goiters",
|
| 677 |
+
"gonorrhoea": "gonorrhea",
|
| 678 |
+
"gramme": "gram",
|
| 679 |
+
"grammes": "grams",
|
| 680 |
+
"gravelled": "graveled",
|
| 681 |
+
"grey": "gray",
|
| 682 |
+
"greyed": "grayed",
|
| 683 |
+
"greying": "graying",
|
| 684 |
+
"greyish": "grayish",
|
| 685 |
+
"greyness": "grayness",
|
| 686 |
+
"greys": "grays",
|
| 687 |
+
"grovelled": "groveled",
|
| 688 |
+
"grovelling": "groveling",
|
| 689 |
+
"groyne": "groin",
|
| 690 |
+
"groynes": "groins",
|
| 691 |
+
"gruelling": "grueling",
|
| 692 |
+
"gruellingly": "gruelingly",
|
| 693 |
+
"gryphon": "griffin",
|
| 694 |
+
"gryphons": "griffins",
|
| 695 |
+
"gynaecological": "gynecological",
|
| 696 |
+
"gynaecologist": "gynecologist",
|
| 697 |
+
"gynaecologists": "gynecologists",
|
| 698 |
+
"gynaecology": "gynecology",
|
| 699 |
+
"haematological": "hematological",
|
| 700 |
+
"haematologist": "hematologist",
|
| 701 |
+
"haematologists": "hematologists",
|
| 702 |
+
"haematology": "hematology",
|
| 703 |
+
"haemoglobin": "hemoglobin",
|
| 704 |
+
"haemophilia": "hemophilia",
|
| 705 |
+
"haemophiliac": "hemophiliac",
|
| 706 |
+
"haemophiliacs": "hemophiliacs",
|
| 707 |
+
"haemorrhage": "hemorrhage",
|
| 708 |
+
"haemorrhaged": "hemorrhaged",
|
| 709 |
+
"haemorrhages": "hemorrhages",
|
| 710 |
+
"haemorrhaging": "hemorrhaging",
|
| 711 |
+
"haemorrhoids": "hemorrhoids",
|
| 712 |
+
"harbour": "harbor",
|
| 713 |
+
"harboured": "harbored",
|
| 714 |
+
"harbouring": "harboring",
|
| 715 |
+
"harbours": "harbors",
|
| 716 |
+
"harmonisation": "harmonization",
|
| 717 |
+
"harmonise": "harmonize",
|
| 718 |
+
"harmonised": "harmonized",
|
| 719 |
+
"harmonises": "harmonizes",
|
| 720 |
+
"harmonising": "harmonizing",
|
| 721 |
+
"homoeopath": "homeopath",
|
| 722 |
+
"homoeopathic": "homeopathic",
|
| 723 |
+
"homoeopaths": "homeopaths",
|
| 724 |
+
"homoeopathy": "homeopathy",
|
| 725 |
+
"homogenise": "homogenize",
|
| 726 |
+
"homogenised": "homogenized",
|
| 727 |
+
"homogenises": "homogenizes",
|
| 728 |
+
"homogenising": "homogenizing",
|
| 729 |
+
"honour": "honor",
|
| 730 |
+
"honourable": "honorable",
|
| 731 |
+
"honourably": "honorably",
|
| 732 |
+
"honoured": "honored",
|
| 733 |
+
"honouring": "honoring",
|
| 734 |
+
"honours": "honors",
|
| 735 |
+
"hospitalisation": "hospitalization",
|
| 736 |
+
"hospitalise": "hospitalize",
|
| 737 |
+
"hospitalised": "hospitalized",
|
| 738 |
+
"hospitalises": "hospitalizes",
|
| 739 |
+
"hospitalising": "hospitalizing",
|
| 740 |
+
"humanise": "humanize",
|
| 741 |
+
"humanised": "humanized",
|
| 742 |
+
"humanises": "humanizes",
|
| 743 |
+
"humanising": "humanizing",
|
| 744 |
+
"humour": "humor",
|
| 745 |
+
"humoured": "humored",
|
| 746 |
+
"humouring": "humoring",
|
| 747 |
+
"humourless": "humorless",
|
| 748 |
+
"humours": "humors",
|
| 749 |
+
"hybridise": "hybridize",
|
| 750 |
+
"hybridised": "hybridized",
|
| 751 |
+
"hybridises": "hybridizes",
|
| 752 |
+
"hybridising": "hybridizing",
|
| 753 |
+
"hypnotise": "hypnotize",
|
| 754 |
+
"hypnotised": "hypnotized",
|
| 755 |
+
"hypnotises": "hypnotizes",
|
| 756 |
+
"hypnotising": "hypnotizing",
|
| 757 |
+
"hypothesise": "hypothesize",
|
| 758 |
+
"hypothesised": "hypothesized",
|
| 759 |
+
"hypothesises": "hypothesizes",
|
| 760 |
+
"hypothesising": "hypothesizing",
|
| 761 |
+
"idealisation": "idealization",
|
| 762 |
+
"idealise": "idealize",
|
| 763 |
+
"idealised": "idealized",
|
| 764 |
+
"idealises": "idealizes",
|
| 765 |
+
"idealising": "idealizing",
|
| 766 |
+
"idolise": "idolize",
|
| 767 |
+
"idolised": "idolized",
|
| 768 |
+
"idolises": "idolizes",
|
| 769 |
+
"idolising": "idolizing",
|
| 770 |
+
"immobilisation": "immobilization",
|
| 771 |
+
"immobilise": "immobilize",
|
| 772 |
+
"immobilised": "immobilized",
|
| 773 |
+
"immobiliser": "immobilizer",
|
| 774 |
+
"immobilisers": "immobilizers",
|
| 775 |
+
"immobilises": "immobilizes",
|
| 776 |
+
"immobilising": "immobilizing",
|
| 777 |
+
"immortalise": "immortalize",
|
| 778 |
+
"immortalised": "immortalized",
|
| 779 |
+
"immortalises": "immortalizes",
|
| 780 |
+
"immortalising": "immortalizing",
|
| 781 |
+
"immunisation": "immunization",
|
| 782 |
+
"immunise": "immunize",
|
| 783 |
+
"immunised": "immunized",
|
| 784 |
+
"immunises": "immunizes",
|
| 785 |
+
"immunising": "immunizing",
|
| 786 |
+
"impanelled": "impaneled",
|
| 787 |
+
"impanelling": "impaneling",
|
| 788 |
+
"imperilled": "imperiled",
|
| 789 |
+
"imperilling": "imperiling",
|
| 790 |
+
"individualise": "individualize",
|
| 791 |
+
"individualised": "individualized",
|
| 792 |
+
"individualises": "individualizes",
|
| 793 |
+
"individualising": "individualizing",
|
| 794 |
+
"industrialise": "industrialize",
|
| 795 |
+
"industrialised": "industrialized",
|
| 796 |
+
"industrialises": "industrializes",
|
| 797 |
+
"industrialising": "industrializing",
|
| 798 |
+
"inflexion": "inflection",
|
| 799 |
+
"inflexions": "inflections",
|
| 800 |
+
"initialise": "initialize",
|
| 801 |
+
"initialised": "initialized",
|
| 802 |
+
"initialises": "initializes",
|
| 803 |
+
"initialising": "initializing",
|
| 804 |
+
"initialled": "initialed",
|
| 805 |
+
"initialling": "initialing",
|
| 806 |
+
"instal": "install",
|
| 807 |
+
"instalment": "installment",
|
| 808 |
+
"instalments": "installments",
|
| 809 |
+
"instals": "installs",
|
| 810 |
+
"instil": "instill",
|
| 811 |
+
"instils": "instills",
|
| 812 |
+
"institutionalisation": "institutionalization",
|
| 813 |
+
"institutionalise": "institutionalize",
|
| 814 |
+
"institutionalised": "institutionalized",
|
| 815 |
+
"institutionalises": "institutionalizes",
|
| 816 |
+
"institutionalising": "institutionalizing",
|
| 817 |
+
"intellectualise": "intellectualize",
|
| 818 |
+
"intellectualised": "intellectualized",
|
| 819 |
+
"intellectualises": "intellectualizes",
|
| 820 |
+
"intellectualising": "intellectualizing",
|
| 821 |
+
"internalisation": "internalization",
|
| 822 |
+
"internalise": "internalize",
|
| 823 |
+
"internalised": "internalized",
|
| 824 |
+
"internalises": "internalizes",
|
| 825 |
+
"internalising": "internalizing",
|
| 826 |
+
"internationalisation": "internationalization",
|
| 827 |
+
"internationalise": "internationalize",
|
| 828 |
+
"internationalised": "internationalized",
|
| 829 |
+
"internationalises": "internationalizes",
|
| 830 |
+
"internationalising": "internationalizing",
|
| 831 |
+
"ionisation": "ionization",
|
| 832 |
+
"ionise": "ionize",
|
| 833 |
+
"ionised": "ionized",
|
| 834 |
+
"ioniser": "ionizer",
|
| 835 |
+
"ionisers": "ionizers",
|
| 836 |
+
"ionises": "ionizes",
|
| 837 |
+
"ionising": "ionizing",
|
| 838 |
+
"italicise": "italicize",
|
| 839 |
+
"italicised": "italicized",
|
| 840 |
+
"italicises": "italicizes",
|
| 841 |
+
"italicising": "italicizing",
|
| 842 |
+
"itemise": "itemize",
|
| 843 |
+
"itemised": "itemized",
|
| 844 |
+
"itemises": "itemizes",
|
| 845 |
+
"itemising": "itemizing",
|
| 846 |
+
"jeopardise": "jeopardize",
|
| 847 |
+
"jeopardised": "jeopardized",
|
| 848 |
+
"jeopardises": "jeopardizes",
|
| 849 |
+
"jeopardising": "jeopardizing",
|
| 850 |
+
"jewelled": "jeweled",
|
| 851 |
+
"jeweller": "jeweler",
|
| 852 |
+
"jewellers": "jewelers",
|
| 853 |
+
"jewellery": "jewelry",
|
| 854 |
+
"judgement": "judgment",
|
| 855 |
+
"kilogramme": "kilogram",
|
| 856 |
+
"kilogrammes": "kilograms",
|
| 857 |
+
"kilometre": "kilometer",
|
| 858 |
+
"kilometres": "kilometers",
|
| 859 |
+
"labelled": "labeled",
|
| 860 |
+
"labelling": "labeling",
|
| 861 |
+
"labour": "labor",
|
| 862 |
+
"laboured": "labored",
|
| 863 |
+
"labourer": "laborer",
|
| 864 |
+
"labourers": "laborers",
|
| 865 |
+
"labouring": "laboring",
|
| 866 |
+
"labours": "labors",
|
| 867 |
+
"lacklustre": "lackluster",
|
| 868 |
+
"legalisation": "legalization",
|
| 869 |
+
"legalise": "legalize",
|
| 870 |
+
"legalised": "legalized",
|
| 871 |
+
"legalises": "legalizes",
|
| 872 |
+
"legalising": "legalizing",
|
| 873 |
+
"legitimise": "legitimize",
|
| 874 |
+
"legitimised": "legitimized",
|
| 875 |
+
"legitimises": "legitimizes",
|
| 876 |
+
"legitimising": "legitimizing",
|
| 877 |
+
"leukaemia": "leukemia",
|
| 878 |
+
"levelled": "leveled",
|
| 879 |
+
"leveller": "leveler",
|
| 880 |
+
"levellers": "levelers",
|
| 881 |
+
"levelling": "leveling",
|
| 882 |
+
"libelled": "libeled",
|
| 883 |
+
"libelling": "libeling",
|
| 884 |
+
"libellous": "libelous",
|
| 885 |
+
"liberalisation": "liberalization",
|
| 886 |
+
"liberalise": "liberalize",
|
| 887 |
+
"liberalised": "liberalized",
|
| 888 |
+
"liberalises": "liberalizes",
|
| 889 |
+
"liberalising": "liberalizing",
|
| 890 |
+
"licence": "license",
|
| 891 |
+
"licenced": "licensed",
|
| 892 |
+
"licences": "licenses",
|
| 893 |
+
"licencing": "licensing",
|
| 894 |
+
"likeable": "likable",
|
| 895 |
+
"lionisation": "lionization",
|
| 896 |
+
"lionise": "lionize",
|
| 897 |
+
"lionised": "lionized",
|
| 898 |
+
"lionises": "lionizes",
|
| 899 |
+
"lionising": "lionizing",
|
| 900 |
+
"liquidise": "liquidize",
|
| 901 |
+
"liquidised": "liquidized",
|
| 902 |
+
"liquidiser": "liquidizer",
|
| 903 |
+
"liquidisers": "liquidizers",
|
| 904 |
+
"liquidises": "liquidizes",
|
| 905 |
+
"liquidising": "liquidizing",
|
| 906 |
+
"litre": "liter",
|
| 907 |
+
"litres": "liters",
|
| 908 |
+
"localise": "localize",
|
| 909 |
+
"localised": "localized",
|
| 910 |
+
"localises": "localizes",
|
| 911 |
+
"localising": "localizing",
|
| 912 |
+
"louvre": "louver",
|
| 913 |
+
"louvred": "louvered",
|
| 914 |
+
"louvres": "louvers",
|
| 915 |
+
"lustre": "luster",
|
| 916 |
+
"magnetise": "magnetize",
|
| 917 |
+
"magnetised": "magnetized",
|
| 918 |
+
"magnetises": "magnetizes",
|
| 919 |
+
"magnetising": "magnetizing",
|
| 920 |
+
"manoeuvrability": "maneuverability",
|
| 921 |
+
"manoeuvrable": "maneuverable",
|
| 922 |
+
"manoeuvre": "maneuver",
|
| 923 |
+
"manoeuvred": "maneuvered",
|
| 924 |
+
"manoeuvres": "maneuvers",
|
| 925 |
+
"manoeuvring": "maneuvering",
|
| 926 |
+
"manoeuvrings": "maneuverings",
|
| 927 |
+
"marginalisation": "marginalization",
|
| 928 |
+
"marginalise": "marginalize",
|
| 929 |
+
"marginalised": "marginalized",
|
| 930 |
+
"marginalises": "marginalizes",
|
| 931 |
+
"marginalising": "marginalizing",
|
| 932 |
+
"marshalled": "marshaled",
|
| 933 |
+
"marshalling": "marshaling",
|
| 934 |
+
"marvelled": "marveled",
|
| 935 |
+
"marvelling": "marveling",
|
| 936 |
+
"marvellous": "marvelous",
|
| 937 |
+
"marvellously": "marvelously",
|
| 938 |
+
"materialisation": "materialization",
|
| 939 |
+
"materialise": "materialize",
|
| 940 |
+
"materialised": "materialized",
|
| 941 |
+
"materialises": "materializes",
|
| 942 |
+
"materialising": "materializing",
|
| 943 |
+
"maximisation": "maximization",
|
| 944 |
+
"maximise": "maximize",
|
| 945 |
+
"maximised": "maximized",
|
| 946 |
+
"maximises": "maximizes",
|
| 947 |
+
"maximising": "maximizing",
|
| 948 |
+
"meagre": "meager",
|
| 949 |
+
"mechanisation": "mechanization",
|
| 950 |
+
"mechanise": "mechanize",
|
| 951 |
+
"mechanised": "mechanized",
|
| 952 |
+
"mechanises": "mechanizes",
|
| 953 |
+
"mechanising": "mechanizing",
|
| 954 |
+
"mediaeval": "medieval",
|
| 955 |
+
"memorialise": "memorialize",
|
| 956 |
+
"memorialised": "memorialized",
|
| 957 |
+
"memorialises": "memorializes",
|
| 958 |
+
"memorialising": "memorializing",
|
| 959 |
+
"memorise": "memorize",
|
| 960 |
+
"memorised": "memorized",
|
| 961 |
+
"memorises": "memorizes",
|
| 962 |
+
"memorising": "memorizing",
|
| 963 |
+
"mesmerise": "mesmerize",
|
| 964 |
+
"mesmerised": "mesmerized",
|
| 965 |
+
"mesmerises": "mesmerizes",
|
| 966 |
+
"mesmerising": "mesmerizing",
|
| 967 |
+
"metabolise": "metabolize",
|
| 968 |
+
"metabolised": "metabolized",
|
| 969 |
+
"metabolises": "metabolizes",
|
| 970 |
+
"metabolising": "metabolizing",
|
| 971 |
+
"metre": "meter",
|
| 972 |
+
"metres": "meters",
|
| 973 |
+
"mhm": "hmm",
|
| 974 |
+
"micrometre": "micrometer",
|
| 975 |
+
"micrometres": "micrometers",
|
| 976 |
+
"militarise": "militarize",
|
| 977 |
+
"militarised": "militarized",
|
| 978 |
+
"militarises": "militarizes",
|
| 979 |
+
"militarising": "militarizing",
|
| 980 |
+
"milligramme": "milligram",
|
| 981 |
+
"milligrammes": "milligrams",
|
| 982 |
+
"millilitre": "milliliter",
|
| 983 |
+
"millilitres": "milliliters",
|
| 984 |
+
"millimetre": "millimeter",
|
| 985 |
+
"millimetres": "millimeters",
|
| 986 |
+
"miniaturisation": "miniaturization",
|
| 987 |
+
"miniaturise": "miniaturize",
|
| 988 |
+
"miniaturised": "miniaturized",
|
| 989 |
+
"miniaturises": "miniaturizes",
|
| 990 |
+
"miniaturising": "miniaturizing",
|
| 991 |
+
"minibusses": "minibuses",
|
| 992 |
+
"minimise": "minimize",
|
| 993 |
+
"minimised": "minimized",
|
| 994 |
+
"minimises": "minimizes",
|
| 995 |
+
"minimising": "minimizing",
|
| 996 |
+
"misbehaviour": "misbehavior",
|
| 997 |
+
"misdemeanour": "misdemeanor",
|
| 998 |
+
"misdemeanours": "misdemeanors",
|
| 999 |
+
"misspelt": "misspelled",
|
| 1000 |
+
"mitre": "miter",
|
| 1001 |
+
"mitres": "miters",
|
| 1002 |
+
"mm": "hmm",
|
| 1003 |
+
"mmm": "hmm",
|
| 1004 |
+
"mobilisation": "mobilization",
|
| 1005 |
+
"mobilise": "mobilize",
|
| 1006 |
+
"mobilised": "mobilized",
|
| 1007 |
+
"mobilises": "mobilizes",
|
| 1008 |
+
"mobilising": "mobilizing",
|
| 1009 |
+
"modelled": "modeled",
|
| 1010 |
+
"modeller": "modeler",
|
| 1011 |
+
"modellers": "modelers",
|
| 1012 |
+
"modelling": "modeling",
|
| 1013 |
+
"modernise": "modernize",
|
| 1014 |
+
"modernised": "modernized",
|
| 1015 |
+
"modernises": "modernizes",
|
| 1016 |
+
"modernising": "modernizing",
|
| 1017 |
+
"moisturise": "moisturize",
|
| 1018 |
+
"moisturised": "moisturized",
|
| 1019 |
+
"moisturiser": "moisturizer",
|
| 1020 |
+
"moisturisers": "moisturizers",
|
| 1021 |
+
"moisturises": "moisturizes",
|
| 1022 |
+
"moisturising": "moisturizing",
|
| 1023 |
+
"monologue": "monolog",
|
| 1024 |
+
"monologues": "monologs",
|
| 1025 |
+
"monopolisation": "monopolization",
|
| 1026 |
+
"monopolise": "monopolize",
|
| 1027 |
+
"monopolised": "monopolized",
|
| 1028 |
+
"monopolises": "monopolizes",
|
| 1029 |
+
"monopolising": "monopolizing",
|
| 1030 |
+
"moralise": "moralize",
|
| 1031 |
+
"moralised": "moralized",
|
| 1032 |
+
"moralises": "moralizes",
|
| 1033 |
+
"moralising": "moralizing",
|
| 1034 |
+
"motorised": "motorized",
|
| 1035 |
+
"mould": "mold",
|
| 1036 |
+
"moulded": "molded",
|
| 1037 |
+
"moulder": "molder",
|
| 1038 |
+
"mouldered": "moldered",
|
| 1039 |
+
"mouldering": "moldering",
|
| 1040 |
+
"moulders": "molders",
|
| 1041 |
+
"mouldier": "moldier",
|
| 1042 |
+
"mouldiest": "moldiest",
|
| 1043 |
+
"moulding": "molding",
|
| 1044 |
+
"mouldings": "moldings",
|
| 1045 |
+
"moulds": "molds",
|
| 1046 |
+
"mouldy": "moldy",
|
| 1047 |
+
"moult": "molt",
|
| 1048 |
+
"moulted": "molted",
|
| 1049 |
+
"moulting": "molting",
|
| 1050 |
+
"moults": "molts",
|
| 1051 |
+
"moustache": "mustache",
|
| 1052 |
+
"moustached": "mustached",
|
| 1053 |
+
"moustaches": "mustaches",
|
| 1054 |
+
"moustachioed": "mustachioed",
|
| 1055 |
+
"multicoloured": "multicolored",
|
| 1056 |
+
"nationalisation": "nationalization",
|
| 1057 |
+
"nationalisations": "nationalizations",
|
| 1058 |
+
"nationalise": "nationalize",
|
| 1059 |
+
"nationalised": "nationalized",
|
| 1060 |
+
"nationalises": "nationalizes",
|
| 1061 |
+
"nationalising": "nationalizing",
|
| 1062 |
+
"naturalisation": "naturalization",
|
| 1063 |
+
"naturalise": "naturalize",
|
| 1064 |
+
"naturalised": "naturalized",
|
| 1065 |
+
"naturalises": "naturalizes",
|
| 1066 |
+
"naturalising": "naturalizing",
|
| 1067 |
+
"neighbour": "neighbor",
|
| 1068 |
+
"neighbourhood": "neighborhood",
|
| 1069 |
+
"neighbourhoods": "neighborhoods",
|
| 1070 |
+
"neighbouring": "neighboring",
|
| 1071 |
+
"neighbourliness": "neighborliness",
|
| 1072 |
+
"neighbourly": "neighborly",
|
| 1073 |
+
"neighbours": "neighbors",
|
| 1074 |
+
"neutralisation": "neutralization",
|
| 1075 |
+
"neutralise": "neutralize",
|
| 1076 |
+
"neutralised": "neutralized",
|
| 1077 |
+
"neutralises": "neutralizes",
|
| 1078 |
+
"neutralising": "neutralizing",
|
| 1079 |
+
"normalisation": "normalization",
|
| 1080 |
+
"normalise": "normalize",
|
| 1081 |
+
"normalised": "normalized",
|
| 1082 |
+
"normalises": "normalizes",
|
| 1083 |
+
"normalising": "normalizing",
|
| 1084 |
+
"odour": "odor",
|
| 1085 |
+
"odourless": "odorless",
|
| 1086 |
+
"odours": "odors",
|
| 1087 |
+
"oesophagus": "esophagus",
|
| 1088 |
+
"oesophaguses": "esophaguses",
|
| 1089 |
+
"oestrogen": "estrogen",
|
| 1090 |
+
"offence": "offense",
|
| 1091 |
+
"offences": "offenses",
|
| 1092 |
+
"omelette": "omelet",
|
| 1093 |
+
"omelettes": "omelets",
|
| 1094 |
+
"optimise": "optimize",
|
| 1095 |
+
"optimised": "optimized",
|
| 1096 |
+
"optimises": "optimizes",
|
| 1097 |
+
"optimising": "optimizing",
|
| 1098 |
+
"organisation": "organization",
|
| 1099 |
+
"organisational": "organizational",
|
| 1100 |
+
"organisations": "organizations",
|
| 1101 |
+
"organise": "organize",
|
| 1102 |
+
"organised": "organized",
|
| 1103 |
+
"organiser": "organizer",
|
| 1104 |
+
"organisers": "organizers",
|
| 1105 |
+
"organises": "organizes",
|
| 1106 |
+
"organising": "organizing",
|
| 1107 |
+
"orthopaedic": "orthopedic",
|
| 1108 |
+
"orthopaedics": "orthopedics",
|
| 1109 |
+
"ostracise": "ostracize",
|
| 1110 |
+
"ostracised": "ostracized",
|
| 1111 |
+
"ostracises": "ostracizes",
|
| 1112 |
+
"ostracising": "ostracizing",
|
| 1113 |
+
"outmanoeuvre": "outmaneuver",
|
| 1114 |
+
"outmanoeuvred": "outmaneuvered",
|
| 1115 |
+
"outmanoeuvres": "outmaneuvers",
|
| 1116 |
+
"outmanoeuvring": "outmaneuvering",
|
| 1117 |
+
"overemphasise": "overemphasize",
|
| 1118 |
+
"overemphasised": "overemphasized",
|
| 1119 |
+
"overemphasises": "overemphasizes",
|
| 1120 |
+
"overemphasising": "overemphasizing",
|
| 1121 |
+
"oxidisation": "oxidization",
|
| 1122 |
+
"oxidise": "oxidize",
|
| 1123 |
+
"oxidised": "oxidized",
|
| 1124 |
+
"oxidises": "oxidizes",
|
| 1125 |
+
"oxidising": "oxidizing",
|
| 1126 |
+
"paederast": "pederast",
|
| 1127 |
+
"paederasts": "pederasts",
|
| 1128 |
+
"paediatric": "pediatric",
|
| 1129 |
+
"paediatrician": "pediatrician",
|
| 1130 |
+
"paediatricians": "pediatricians",
|
| 1131 |
+
"paediatrics": "pediatrics",
|
| 1132 |
+
"paedophile": "pedophile",
|
| 1133 |
+
"paedophiles": "pedophiles",
|
| 1134 |
+
"paedophilia": "pedophilia",
|
| 1135 |
+
"palaeolithic": "paleolithic",
|
| 1136 |
+
"palaeontologist": "paleontologist",
|
| 1137 |
+
"palaeontologists": "paleontologists",
|
| 1138 |
+
"palaeontology": "paleontology",
|
| 1139 |
+
"panelled": "paneled",
|
| 1140 |
+
"panelling": "paneling",
|
| 1141 |
+
"panellist": "panelist",
|
| 1142 |
+
"panellists": "panelists",
|
| 1143 |
+
"paralyse": "paralyze",
|
| 1144 |
+
"paralysed": "paralyzed",
|
| 1145 |
+
"paralyses": "paralyzes",
|
| 1146 |
+
"paralysing": "paralyzing",
|
| 1147 |
+
"parcelled": "parceled",
|
| 1148 |
+
"parcelling": "parceling",
|
| 1149 |
+
"parlour": "parlor",
|
| 1150 |
+
"parlours": "parlors",
|
| 1151 |
+
"particularise": "particularize",
|
| 1152 |
+
"particularised": "particularized",
|
| 1153 |
+
"particularises": "particularizes",
|
| 1154 |
+
"particularising": "particularizing",
|
| 1155 |
+
"passivisation": "passivization",
|
| 1156 |
+
"passivise": "passivize",
|
| 1157 |
+
"passivised": "passivized",
|
| 1158 |
+
"passivises": "passivizes",
|
| 1159 |
+
"passivising": "passivizing",
|
| 1160 |
+
"pasteurisation": "pasteurization",
|
| 1161 |
+
"pasteurise": "pasteurize",
|
| 1162 |
+
"pasteurised": "pasteurized",
|
| 1163 |
+
"pasteurises": "pasteurizes",
|
| 1164 |
+
"pasteurising": "pasteurizing",
|
| 1165 |
+
"patronise": "patronize",
|
| 1166 |
+
"patronised": "patronized",
|
| 1167 |
+
"patronises": "patronizes",
|
| 1168 |
+
"patronising": "patronizing",
|
| 1169 |
+
"patronisingly": "patronizingly",
|
| 1170 |
+
"pedalled": "pedaled",
|
| 1171 |
+
"pedalling": "pedaling",
|
| 1172 |
+
"pedestrianisation": "pedestrianization",
|
| 1173 |
+
"pedestrianise": "pedestrianize",
|
| 1174 |
+
"pedestrianised": "pedestrianized",
|
| 1175 |
+
"pedestrianises": "pedestrianizes",
|
| 1176 |
+
"pedestrianising": "pedestrianizing",
|
| 1177 |
+
"penalise": "penalize",
|
| 1178 |
+
"penalised": "penalized",
|
| 1179 |
+
"penalises": "penalizes",
|
| 1180 |
+
"penalising": "penalizing",
|
| 1181 |
+
"pencilled": "penciled",
|
| 1182 |
+
"pencilling": "penciling",
|
| 1183 |
+
"personalise": "personalize",
|
| 1184 |
+
"personalised": "personalized",
|
| 1185 |
+
"personalises": "personalizes",
|
| 1186 |
+
"personalising": "personalizing",
|
| 1187 |
+
"pharmacopoeia": "pharmacopeia",
|
| 1188 |
+
"pharmacopoeias": "pharmacopeias",
|
| 1189 |
+
"philosophise": "philosophize",
|
| 1190 |
+
"philosophised": "philosophized",
|
| 1191 |
+
"philosophises": "philosophizes",
|
| 1192 |
+
"philosophising": "philosophizing",
|
| 1193 |
+
"philtre": "filter",
|
| 1194 |
+
"philtres": "filters",
|
| 1195 |
+
"phoney": "phony",
|
| 1196 |
+
"plagiarise": "plagiarize",
|
| 1197 |
+
"plagiarised": "plagiarized",
|
| 1198 |
+
"plagiarises": "plagiarizes",
|
| 1199 |
+
"plagiarising": "plagiarizing",
|
| 1200 |
+
"plough": "plow",
|
| 1201 |
+
"ploughed": "plowed",
|
| 1202 |
+
"ploughing": "plowing",
|
| 1203 |
+
"ploughman": "plowman",
|
| 1204 |
+
"ploughmen": "plowmen",
|
| 1205 |
+
"ploughs": "plows",
|
| 1206 |
+
"ploughshare": "plowshare",
|
| 1207 |
+
"ploughshares": "plowshares",
|
| 1208 |
+
"polarisation": "polarization",
|
| 1209 |
+
"polarise": "polarize",
|
| 1210 |
+
"polarised": "polarized",
|
| 1211 |
+
"polarises": "polarizes",
|
| 1212 |
+
"polarising": "polarizing",
|
| 1213 |
+
"politicisation": "politicization",
|
| 1214 |
+
"politicise": "politicize",
|
| 1215 |
+
"politicised": "politicized",
|
| 1216 |
+
"politicises": "politicizes",
|
| 1217 |
+
"politicising": "politicizing",
|
| 1218 |
+
"popularisation": "popularization",
|
| 1219 |
+
"popularise": "popularize",
|
| 1220 |
+
"popularised": "popularized",
|
| 1221 |
+
"popularises": "popularizes",
|
| 1222 |
+
"popularising": "popularizing",
|
| 1223 |
+
"pouffe": "pouf",
|
| 1224 |
+
"pouffes": "poufs",
|
| 1225 |
+
"practise": "practice",
|
| 1226 |
+
"practised": "practiced",
|
| 1227 |
+
"practises": "practices",
|
| 1228 |
+
"practising": "practicing",
|
| 1229 |
+
"praesidium": "presidium",
|
| 1230 |
+
"praesidiums": "presidiums",
|
| 1231 |
+
"pressurisation": "pressurization",
|
| 1232 |
+
"pressurise": "pressurize",
|
| 1233 |
+
"pressurised": "pressurized",
|
| 1234 |
+
"pressurises": "pressurizes",
|
| 1235 |
+
"pressurising": "pressurizing",
|
| 1236 |
+
"pretence": "pretense",
|
| 1237 |
+
"pretences": "pretenses",
|
| 1238 |
+
"primaeval": "primeval",
|
| 1239 |
+
"prioritisation": "prioritization",
|
| 1240 |
+
"prioritise": "prioritize",
|
| 1241 |
+
"prioritised": "prioritized",
|
| 1242 |
+
"prioritises": "prioritizes",
|
| 1243 |
+
"prioritising": "prioritizing",
|
| 1244 |
+
"privatisation": "privatization",
|
| 1245 |
+
"privatisations": "privatizations",
|
| 1246 |
+
"privatise": "privatize",
|
| 1247 |
+
"privatised": "privatized",
|
| 1248 |
+
"privatises": "privatizes",
|
| 1249 |
+
"privatising": "privatizing",
|
| 1250 |
+
"professionalisation": "professionalization",
|
| 1251 |
+
"professionalise": "professionalize",
|
| 1252 |
+
"professionalised": "professionalized",
|
| 1253 |
+
"professionalises": "professionalizes",
|
| 1254 |
+
"professionalising": "professionalizing",
|
| 1255 |
+
"programme": "program",
|
| 1256 |
+
"programmes": "programs",
|
| 1257 |
+
"prologue": "prolog",
|
| 1258 |
+
"prologues": "prologs",
|
| 1259 |
+
"propagandise": "propagandize",
|
| 1260 |
+
"propagandised": "propagandized",
|
| 1261 |
+
"propagandises": "propagandizes",
|
| 1262 |
+
"propagandising": "propagandizing",
|
| 1263 |
+
"proselytise": "proselytize",
|
| 1264 |
+
"proselytised": "proselytized",
|
| 1265 |
+
"proselytiser": "proselytizer",
|
| 1266 |
+
"proselytisers": "proselytizers",
|
| 1267 |
+
"proselytises": "proselytizes",
|
| 1268 |
+
"proselytising": "proselytizing",
|
| 1269 |
+
"psychoanalyse": "psychoanalyze",
|
| 1270 |
+
"psychoanalysed": "psychoanalyzed",
|
| 1271 |
+
"psychoanalyses": "psychoanalyzes",
|
| 1272 |
+
"psychoanalysing": "psychoanalyzing",
|
| 1273 |
+
"publicise": "publicize",
|
| 1274 |
+
"publicised": "publicized",
|
| 1275 |
+
"publicises": "publicizes",
|
| 1276 |
+
"publicising": "publicizing",
|
| 1277 |
+
"pulverisation": "pulverization",
|
| 1278 |
+
"pulverise": "pulverize",
|
| 1279 |
+
"pulverised": "pulverized",
|
| 1280 |
+
"pulverises": "pulverizes",
|
| 1281 |
+
"pulverising": "pulverizing",
|
| 1282 |
+
"pummelled": "pummel",
|
| 1283 |
+
"pummelling": "pummeled",
|
| 1284 |
+
"pyjama": "pajama",
|
| 1285 |
+
"pyjamas": "pajamas",
|
| 1286 |
+
"pzazz": "pizzazz",
|
| 1287 |
+
"quarrelled": "quarreled",
|
| 1288 |
+
"quarrelling": "quarreling",
|
| 1289 |
+
"radicalise": "radicalize",
|
| 1290 |
+
"radicalised": "radicalized",
|
| 1291 |
+
"radicalises": "radicalizes",
|
| 1292 |
+
"radicalising": "radicalizing",
|
| 1293 |
+
"rancour": "rancor",
|
| 1294 |
+
"randomise": "randomize",
|
| 1295 |
+
"randomised": "randomized",
|
| 1296 |
+
"randomises": "randomizes",
|
| 1297 |
+
"randomising": "randomizing",
|
| 1298 |
+
"rationalisation": "rationalization",
|
| 1299 |
+
"rationalisations": "rationalizations",
|
| 1300 |
+
"rationalise": "rationalize",
|
| 1301 |
+
"rationalised": "rationalized",
|
| 1302 |
+
"rationalises": "rationalizes",
|
| 1303 |
+
"rationalising": "rationalizing",
|
| 1304 |
+
"ravelled": "raveled",
|
| 1305 |
+
"ravelling": "raveling",
|
| 1306 |
+
"realisable": "realizable",
|
| 1307 |
+
"realisation": "realization",
|
| 1308 |
+
"realisations": "realizations",
|
| 1309 |
+
"realise": "realize",
|
| 1310 |
+
"realised": "realized",
|
| 1311 |
+
"realises": "realizes",
|
| 1312 |
+
"realising": "realizing",
|
| 1313 |
+
"recognisable": "recognizable",
|
| 1314 |
+
"recognisably": "recognizably",
|
| 1315 |
+
"recognisance": "recognizance",
|
| 1316 |
+
"recognise": "recognize",
|
| 1317 |
+
"recognised": "recognized",
|
| 1318 |
+
"recognises": "recognizes",
|
| 1319 |
+
"recognising": "recognizing",
|
| 1320 |
+
"reconnoitre": "reconnoiter",
|
| 1321 |
+
"reconnoitred": "reconnoitered",
|
| 1322 |
+
"reconnoitres": "reconnoiters",
|
| 1323 |
+
"reconnoitring": "reconnoitering",
|
| 1324 |
+
"refuelled": "refueled",
|
| 1325 |
+
"refuelling": "refueling",
|
| 1326 |
+
"regularisation": "regularization",
|
| 1327 |
+
"regularise": "regularize",
|
| 1328 |
+
"regularised": "regularized",
|
| 1329 |
+
"regularises": "regularizes",
|
| 1330 |
+
"regularising": "regularizing",
|
| 1331 |
+
"remodelled": "remodeled",
|
| 1332 |
+
"remodelling": "remodeling",
|
| 1333 |
+
"remould": "remold",
|
| 1334 |
+
"remoulded": "remolded",
|
| 1335 |
+
"remoulding": "remolding",
|
| 1336 |
+
"remoulds": "remolds",
|
| 1337 |
+
"reorganisation": "reorganization",
|
| 1338 |
+
"reorganisations": "reorganizations",
|
| 1339 |
+
"reorganise": "reorganize",
|
| 1340 |
+
"reorganised": "reorganized",
|
| 1341 |
+
"reorganises": "reorganizes",
|
| 1342 |
+
"reorganising": "reorganizing",
|
| 1343 |
+
"revelled": "reveled",
|
| 1344 |
+
"reveller": "reveler",
|
| 1345 |
+
"revellers": "revelers",
|
| 1346 |
+
"revelling": "reveling",
|
| 1347 |
+
"revitalise": "revitalize",
|
| 1348 |
+
"revitalised": "revitalized",
|
| 1349 |
+
"revitalises": "revitalizes",
|
| 1350 |
+
"revitalising": "revitalizing",
|
| 1351 |
+
"revolutionise": "revolutionize",
|
| 1352 |
+
"revolutionised": "revolutionized",
|
| 1353 |
+
"revolutionises": "revolutionizes",
|
| 1354 |
+
"revolutionising": "revolutionizing",
|
| 1355 |
+
"rhapsodise": "rhapsodize",
|
| 1356 |
+
"rhapsodised": "rhapsodized",
|
| 1357 |
+
"rhapsodises": "rhapsodizes",
|
| 1358 |
+
"rhapsodising": "rhapsodizing",
|
| 1359 |
+
"rigour": "rigor",
|
| 1360 |
+
"rigours": "rigors",
|
| 1361 |
+
"ritualised": "ritualized",
|
| 1362 |
+
"rivalled": "rivaled",
|
| 1363 |
+
"rivalling": "rivaling",
|
| 1364 |
+
"romanticise": "romanticize",
|
| 1365 |
+
"romanticised": "romanticized",
|
| 1366 |
+
"romanticises": "romanticizes",
|
| 1367 |
+
"romanticising": "romanticizing",
|
| 1368 |
+
"rumour": "rumor",
|
| 1369 |
+
"rumoured": "rumored",
|
| 1370 |
+
"rumours": "rumors",
|
| 1371 |
+
"sabre": "saber",
|
| 1372 |
+
"sabres": "sabers",
|
| 1373 |
+
"saltpetre": "saltpeter",
|
| 1374 |
+
"sanitise": "sanitize",
|
| 1375 |
+
"sanitised": "sanitized",
|
| 1376 |
+
"sanitises": "sanitizes",
|
| 1377 |
+
"sanitising": "sanitizing",
|
| 1378 |
+
"satirise": "satirize",
|
| 1379 |
+
"satirised": "satirized",
|
| 1380 |
+
"satirises": "satirizes",
|
| 1381 |
+
"satirising": "satirizing",
|
| 1382 |
+
"saviour": "savior",
|
| 1383 |
+
"saviours": "saviors",
|
| 1384 |
+
"savour": "savor",
|
| 1385 |
+
"savoured": "savored",
|
| 1386 |
+
"savouries": "savories",
|
| 1387 |
+
"savouring": "savoring",
|
| 1388 |
+
"savours": "savors",
|
| 1389 |
+
"savoury": "savory",
|
| 1390 |
+
"scandalise": "scandalize",
|
| 1391 |
+
"scandalised": "scandalized",
|
| 1392 |
+
"scandalises": "scandalizes",
|
| 1393 |
+
"scandalising": "scandalizing",
|
| 1394 |
+
"sceptic": "skeptic",
|
| 1395 |
+
"sceptical": "skeptical",
|
| 1396 |
+
"sceptically": "skeptically",
|
| 1397 |
+
"scepticism": "skepticism",
|
| 1398 |
+
"sceptics": "skeptics",
|
| 1399 |
+
"sceptre": "scepter",
|
| 1400 |
+
"sceptres": "scepters",
|
| 1401 |
+
"scrutinise": "scrutinize",
|
| 1402 |
+
"scrutinised": "scrutinized",
|
| 1403 |
+
"scrutinises": "scrutinizes",
|
| 1404 |
+
"scrutinising": "scrutinizing",
|
| 1405 |
+
"secularisation": "secularization",
|
| 1406 |
+
"secularise": "secularize",
|
| 1407 |
+
"secularised": "secularized",
|
| 1408 |
+
"secularises": "secularizes",
|
| 1409 |
+
"secularising": "secularizing",
|
| 1410 |
+
"sensationalise": "sensationalize",
|
| 1411 |
+
"sensationalised": "sensationalized",
|
| 1412 |
+
"sensationalises": "sensationalizes",
|
| 1413 |
+
"sensationalising": "sensationalizing",
|
| 1414 |
+
"sensitise": "sensitize",
|
| 1415 |
+
"sensitised": "sensitized",
|
| 1416 |
+
"sensitises": "sensitizes",
|
| 1417 |
+
"sensitising": "sensitizing",
|
| 1418 |
+
"sentimentalise": "sentimentalize",
|
| 1419 |
+
"sentimentalised": "sentimentalized",
|
| 1420 |
+
"sentimentalises": "sentimentalizes",
|
| 1421 |
+
"sentimentalising": "sentimentalizing",
|
| 1422 |
+
"sepulchre": "sepulcher",
|
| 1423 |
+
"sepulchres": "sepulchers",
|
| 1424 |
+
"serialisation": "serialization",
|
| 1425 |
+
"serialisations": "serializations",
|
| 1426 |
+
"serialise": "serialize",
|
| 1427 |
+
"serialised": "serialized",
|
| 1428 |
+
"serialises": "serializes",
|
| 1429 |
+
"serialising": "serializing",
|
| 1430 |
+
"sermonise": "sermonize",
|
| 1431 |
+
"sermonised": "sermonized",
|
| 1432 |
+
"sermonises": "sermonizes",
|
| 1433 |
+
"sermonising": "sermonizing",
|
| 1434 |
+
"sheikh": "sheik",
|
| 1435 |
+
"shovelled": "shoveled",
|
| 1436 |
+
"shovelling": "shoveling",
|
| 1437 |
+
"shrivelled": "shriveled",
|
| 1438 |
+
"shrivelling": "shriveling",
|
| 1439 |
+
"signalise": "signalize",
|
| 1440 |
+
"signalised": "signalized",
|
| 1441 |
+
"signalises": "signalizes",
|
| 1442 |
+
"signalising": "signalizing",
|
| 1443 |
+
"signalled": "signaled",
|
| 1444 |
+
"signalling": "signaling",
|
| 1445 |
+
"smoulder": "smolder",
|
| 1446 |
+
"smouldered": "smoldered",
|
| 1447 |
+
"smouldering": "smoldering",
|
| 1448 |
+
"smoulders": "smolders",
|
| 1449 |
+
"snivelled": "sniveled",
|
| 1450 |
+
"snivelling": "sniveling",
|
| 1451 |
+
"snorkelled": "snorkeled",
|
| 1452 |
+
"snorkelling": "snorkeling",
|
| 1453 |
+
"snowplough": "snowplow",
|
| 1454 |
+
"snowploughs": "snowplow",
|
| 1455 |
+
"socialisation": "socialization",
|
| 1456 |
+
"socialise": "socialize",
|
| 1457 |
+
"socialised": "socialized",
|
| 1458 |
+
"socialises": "socializes",
|
| 1459 |
+
"socialising": "socializing",
|
| 1460 |
+
"sodomise": "sodomize",
|
| 1461 |
+
"sodomised": "sodomized",
|
| 1462 |
+
"sodomises": "sodomizes",
|
| 1463 |
+
"sodomising": "sodomizing",
|
| 1464 |
+
"solemnise": "solemnize",
|
| 1465 |
+
"solemnised": "solemnized",
|
| 1466 |
+
"solemnises": "solemnizes",
|
| 1467 |
+
"solemnising": "solemnizing",
|
| 1468 |
+
"sombre": "somber",
|
| 1469 |
+
"specialisation": "specialization",
|
| 1470 |
+
"specialisations": "specializations",
|
| 1471 |
+
"specialise": "specialize",
|
| 1472 |
+
"specialised": "specialized",
|
| 1473 |
+
"specialises": "specializes",
|
| 1474 |
+
"specialising": "specializing",
|
| 1475 |
+
"spectre": "specter",
|
| 1476 |
+
"spectres": "specters",
|
| 1477 |
+
"spiralled": "spiraled",
|
| 1478 |
+
"spiralling": "spiraling",
|
| 1479 |
+
"splendour": "splendor",
|
| 1480 |
+
"splendours": "splendors",
|
| 1481 |
+
"squirrelled": "squirreled",
|
| 1482 |
+
"squirrelling": "squirreling",
|
| 1483 |
+
"stabilisation": "stabilization",
|
| 1484 |
+
"stabilise": "stabilize",
|
| 1485 |
+
"stabilised": "stabilized",
|
| 1486 |
+
"stabiliser": "stabilizer",
|
| 1487 |
+
"stabilisers": "stabilizers",
|
| 1488 |
+
"stabilises": "stabilizes",
|
| 1489 |
+
"stabilising": "stabilizing",
|
| 1490 |
+
"standardisation": "standardization",
|
| 1491 |
+
"standardise": "standardize",
|
| 1492 |
+
"standardised": "standardized",
|
| 1493 |
+
"standardises": "standardizes",
|
| 1494 |
+
"standardising": "standardizing",
|
| 1495 |
+
"stencilled": "stenciled",
|
| 1496 |
+
"stencilling": "stenciling",
|
| 1497 |
+
"sterilisation": "sterilization",
|
| 1498 |
+
"sterilisations": "sterilizations",
|
| 1499 |
+
"sterilise": "sterilize",
|
| 1500 |
+
"sterilised": "sterilized",
|
| 1501 |
+
"steriliser": "sterilizer",
|
| 1502 |
+
"sterilisers": "sterilizers",
|
| 1503 |
+
"sterilises": "sterilizes",
|
| 1504 |
+
"sterilising": "sterilizing",
|
| 1505 |
+
"stigmatisation": "stigmatization",
|
| 1506 |
+
"stigmatise": "stigmatize",
|
| 1507 |
+
"stigmatised": "stigmatized",
|
| 1508 |
+
"stigmatises": "stigmatizes",
|
| 1509 |
+
"stigmatising": "stigmatizing",
|
| 1510 |
+
"storey": "story",
|
| 1511 |
+
"storeys": "stories",
|
| 1512 |
+
"subsidisation": "subsidization",
|
| 1513 |
+
"subsidise": "subsidize",
|
| 1514 |
+
"subsidised": "subsidized",
|
| 1515 |
+
"subsidiser": "subsidizer",
|
| 1516 |
+
"subsidisers": "subsidizers",
|
| 1517 |
+
"subsidises": "subsidizes",
|
| 1518 |
+
"subsidising": "subsidizing",
|
| 1519 |
+
"succour": "succor",
|
| 1520 |
+
"succoured": "succored",
|
| 1521 |
+
"succouring": "succoring",
|
| 1522 |
+
"succours": "succors",
|
| 1523 |
+
"sulphate": "sulfate",
|
| 1524 |
+
"sulphates": "sulfates",
|
| 1525 |
+
"sulphide": "sulfide",
|
| 1526 |
+
"sulphides": "sulfides",
|
| 1527 |
+
"sulphur": "sulfur",
|
| 1528 |
+
"sulphurous": "sulfurous",
|
| 1529 |
+
"summarise": "summarize",
|
| 1530 |
+
"summarised": "summarized",
|
| 1531 |
+
"summarises": "summarizes",
|
| 1532 |
+
"summarising": "summarizing",
|
| 1533 |
+
"swivelled": "swiveled",
|
| 1534 |
+
"swivelling": "swiveling",
|
| 1535 |
+
"symbolise": "symbolize",
|
| 1536 |
+
"symbolised": "symbolized",
|
| 1537 |
+
"symbolises": "symbolizes",
|
| 1538 |
+
"symbolising": "symbolizing",
|
| 1539 |
+
"sympathise": "sympathize",
|
| 1540 |
+
"sympathised": "sympathized",
|
| 1541 |
+
"sympathiser": "sympathizer",
|
| 1542 |
+
"sympathisers": "sympathizers",
|
| 1543 |
+
"sympathises": "sympathizes",
|
| 1544 |
+
"sympathising": "sympathizing",
|
| 1545 |
+
"synchronisation": "synchronization",
|
| 1546 |
+
"synchronise": "synchronize",
|
| 1547 |
+
"synchronised": "synchronized",
|
| 1548 |
+
"synchronises": "synchronizes",
|
| 1549 |
+
"synchronising": "synchronizing",
|
| 1550 |
+
"synthesise": "synthesize",
|
| 1551 |
+
"synthesised": "synthesized",
|
| 1552 |
+
"synthesiser": "synthesizer",
|
| 1553 |
+
"synthesisers": "synthesizers",
|
| 1554 |
+
"synthesises": "synthesizes",
|
| 1555 |
+
"synthesising": "synthesizing",
|
| 1556 |
+
"syphon": "siphon",
|
| 1557 |
+
"syphoned": "siphoned",
|
| 1558 |
+
"syphoning": "siphoning",
|
| 1559 |
+
"syphons": "siphons",
|
| 1560 |
+
"systematisation": "systematization",
|
| 1561 |
+
"systematise": "systematize",
|
| 1562 |
+
"systematised": "systematized",
|
| 1563 |
+
"systematises": "systematizes",
|
| 1564 |
+
"systematising": "systematizing",
|
| 1565 |
+
"tantalise": "tantalize",
|
| 1566 |
+
"tantalised": "tantalized",
|
| 1567 |
+
"tantalises": "tantalizes",
|
| 1568 |
+
"tantalising": "tantalizing",
|
| 1569 |
+
"tantalisingly": "tantalizingly",
|
| 1570 |
+
"tasselled": "tasseled",
|
| 1571 |
+
"technicolour": "technicolor",
|
| 1572 |
+
"temporise": "temporize",
|
| 1573 |
+
"temporised": "temporized",
|
| 1574 |
+
"temporises": "temporizes",
|
| 1575 |
+
"temporising": "temporizing",
|
| 1576 |
+
"tenderise": "tenderize",
|
| 1577 |
+
"tenderised": "tenderized",
|
| 1578 |
+
"tenderises": "tenderizes",
|
| 1579 |
+
"tenderising": "tenderizing",
|
| 1580 |
+
"terrorise": "terrorize",
|
| 1581 |
+
"terrorised": "terrorized",
|
| 1582 |
+
"terrorises": "terrorizes",
|
| 1583 |
+
"terrorising": "terrorizing",
|
| 1584 |
+
"theatre": "theater",
|
| 1585 |
+
"theatregoer": "theatergoer",
|
| 1586 |
+
"theatregoers": "theatergoers",
|
| 1587 |
+
"theatres": "theaters",
|
| 1588 |
+
"theorise": "theorize",
|
| 1589 |
+
"theorised": "theorized",
|
| 1590 |
+
"theorises": "theorizes",
|
| 1591 |
+
"theorising": "theorizing",
|
| 1592 |
+
"tonne": "ton",
|
| 1593 |
+
"tonnes": "tons",
|
| 1594 |
+
"towelled": "toweled",
|
| 1595 |
+
"towelling": "toweling",
|
| 1596 |
+
"toxaemia": "toxemia",
|
| 1597 |
+
"tranquillise": "tranquilize",
|
| 1598 |
+
"tranquillised": "tranquilized",
|
| 1599 |
+
"tranquilliser": "tranquilizer",
|
| 1600 |
+
"tranquillisers": "tranquilizers",
|
| 1601 |
+
"tranquillises": "tranquilizes",
|
| 1602 |
+
"tranquillising": "tranquilizing",
|
| 1603 |
+
"tranquillity": "tranquility",
|
| 1604 |
+
"tranquillize": "tranquilize",
|
| 1605 |
+
"tranquillized": "tranquilized",
|
| 1606 |
+
"tranquillizer": "tranquilizer",
|
| 1607 |
+
"tranquillizers": "tranquilizers",
|
| 1608 |
+
"tranquillizes": "tranquilizes",
|
| 1609 |
+
"tranquillizing": "tranquilizing",
|
| 1610 |
+
"tranquilly": "tranquility",
|
| 1611 |
+
"transistorised": "transistorized",
|
| 1612 |
+
"traumatise": "traumatize",
|
| 1613 |
+
"traumatised": "traumatized",
|
| 1614 |
+
"traumatises": "traumatizes",
|
| 1615 |
+
"traumatising": "traumatizing",
|
| 1616 |
+
"travelled": "traveled",
|
| 1617 |
+
"traveller": "traveler",
|
| 1618 |
+
"travellers": "travelers",
|
| 1619 |
+
"travelling": "traveling",
|
| 1620 |
+
"travelog": "travelogue",
|
| 1621 |
+
"travelogs": "travelogues",
|
| 1622 |
+
"trialled": "trialed",
|
| 1623 |
+
"trialling": "trialing",
|
| 1624 |
+
"tricolour": "tricolor",
|
| 1625 |
+
"tricolours": "tricolors",
|
| 1626 |
+
"trivialise": "trivialize",
|
| 1627 |
+
"trivialised": "trivialized",
|
| 1628 |
+
"trivialises": "trivializes",
|
| 1629 |
+
"trivialising": "trivializing",
|
| 1630 |
+
"tumour": "tumor",
|
| 1631 |
+
"tumours": "tumors",
|
| 1632 |
+
"tunnelled": "tunneled",
|
| 1633 |
+
"tunnelling": "tunneling",
|
| 1634 |
+
"tyrannise": "tyrannize",
|
| 1635 |
+
"tyrannised": "tyrannized",
|
| 1636 |
+
"tyrannises": "tyrannizes",
|
| 1637 |
+
"tyrannising": "tyrannizing",
|
| 1638 |
+
"tyre": "tire",
|
| 1639 |
+
"tyres": "tires",
|
| 1640 |
+
"unauthorised": "unauthorized",
|
| 1641 |
+
"uncivilised": "uncivilized",
|
| 1642 |
+
"underutilised": "underutilized",
|
| 1643 |
+
"unequalled": "unequaled",
|
| 1644 |
+
"unfavourable": "unfavorable",
|
| 1645 |
+
"unfavourably": "unfavorably",
|
| 1646 |
+
"unionisation": "unionization",
|
| 1647 |
+
"unionise": "unionize",
|
| 1648 |
+
"unionised": "unionized",
|
| 1649 |
+
"unionises": "unionizes",
|
| 1650 |
+
"unionising": "unionizing",
|
| 1651 |
+
"unorganised": "unorganized",
|
| 1652 |
+
"unravelled": "unraveled",
|
| 1653 |
+
"unravelling": "unraveling",
|
| 1654 |
+
"unrecognisable": "unrecognizable",
|
| 1655 |
+
"unrecognised": "unrecognized",
|
| 1656 |
+
"unrivalled": "unrivaled",
|
| 1657 |
+
"unsavoury": "unsavory",
|
| 1658 |
+
"untrammelled": "untrammeled",
|
| 1659 |
+
"urbanisation": "urbanization",
|
| 1660 |
+
"urbanise": "urbanize",
|
| 1661 |
+
"urbanised": "urbanized",
|
| 1662 |
+
"urbanises": "urbanizes",
|
| 1663 |
+
"urbanising": "urbanizing",
|
| 1664 |
+
"utilisable": "utilizable",
|
| 1665 |
+
"utilisation": "utilization",
|
| 1666 |
+
"utilise": "utilize",
|
| 1667 |
+
"utilised": "utilized",
|
| 1668 |
+
"utilises": "utilizes",
|
| 1669 |
+
"utilising": "utilizing",
|
| 1670 |
+
"valour": "valor",
|
| 1671 |
+
"vandalise": "vandalize",
|
| 1672 |
+
"vandalised": "vandalized",
|
| 1673 |
+
"vandalises": "vandalizes",
|
| 1674 |
+
"vandalising": "vandalizing",
|
| 1675 |
+
"vaporisation": "vaporization",
|
| 1676 |
+
"vaporise": "vaporize",
|
| 1677 |
+
"vaporised": "vaporized",
|
| 1678 |
+
"vaporises": "vaporizes",
|
| 1679 |
+
"vaporising": "vaporizing",
|
| 1680 |
+
"vapour": "vapor",
|
| 1681 |
+
"vapours": "vapors",
|
| 1682 |
+
"verbalise": "verbalize",
|
| 1683 |
+
"verbalised": "verbalized",
|
| 1684 |
+
"verbalises": "verbalizes",
|
| 1685 |
+
"verbalising": "verbalizing",
|
| 1686 |
+
"victimisation": "victimization",
|
| 1687 |
+
"victimise": "victimize",
|
| 1688 |
+
"victimised": "victimized",
|
| 1689 |
+
"victimises": "victimizes",
|
| 1690 |
+
"victimising": "victimizing",
|
| 1691 |
+
"videodisc": "videodisk",
|
| 1692 |
+
"videodiscs": "videodisks",
|
| 1693 |
+
"vigour": "vigor",
|
| 1694 |
+
"visualisation": "visualization",
|
| 1695 |
+
"visualisations": "visualizations",
|
| 1696 |
+
"visualise": "visualize",
|
| 1697 |
+
"visualised": "visualized",
|
| 1698 |
+
"visualises": "visualizes",
|
| 1699 |
+
"visualising": "visualizing",
|
| 1700 |
+
"vocalisation": "vocalization",
|
| 1701 |
+
"vocalisations": "vocalizations",
|
| 1702 |
+
"vocalise": "vocalize",
|
| 1703 |
+
"vocalised": "vocalized",
|
| 1704 |
+
"vocalises": "vocalizes",
|
| 1705 |
+
"vocalising": "vocalizing",
|
| 1706 |
+
"vulcanised": "vulcanized",
|
| 1707 |
+
"vulgarisation": "vulgarization",
|
| 1708 |
+
"vulgarise": "vulgarize",
|
| 1709 |
+
"vulgarised": "vulgarized",
|
| 1710 |
+
"vulgarises": "vulgarizes",
|
| 1711 |
+
"vulgarising": "vulgarizing",
|
| 1712 |
+
"waggon": "wagon",
|
| 1713 |
+
"waggons": "wagons",
|
| 1714 |
+
"watercolour": "watercolor",
|
| 1715 |
+
"watercolours": "watercolors",
|
| 1716 |
+
"weaselled": "weaseled",
|
| 1717 |
+
"weaselling": "weaseling",
|
| 1718 |
+
"westernisation": "westernization",
|
| 1719 |
+
"westernise": "westernize",
|
| 1720 |
+
"westernised": "westernized",
|
| 1721 |
+
"westernises": "westernizes",
|
| 1722 |
+
"westernising": "westernizing",
|
| 1723 |
+
"womanise": "womanize",
|
| 1724 |
+
"womanised": "womanized",
|
| 1725 |
+
"womaniser": "womanizer",
|
| 1726 |
+
"womanisers": "womanizers",
|
| 1727 |
+
"womanises": "womanizes",
|
| 1728 |
+
"womanising": "womanizing",
|
| 1729 |
+
"woollen": "woolen",
|
| 1730 |
+
"woollens": "woolens",
|
| 1731 |
+
"woollies": "woolies",
|
| 1732 |
+
"woolly": "wooly",
|
| 1733 |
+
"worshipped": "worshiped",
|
| 1734 |
+
"worshipper": "worshiper",
|
| 1735 |
+
"worshipping": "worshiping",
|
| 1736 |
+
"yodelled": "yodeled",
|
| 1737 |
+
"yodelling": "yodeling",
|
| 1738 |
+
"yoghourt": "yogurt",
|
| 1739 |
+
"yoghourts": "yogurts",
|
| 1740 |
+
"yoghurt": "yogurt",
|
| 1741 |
+
"yoghurts": "yogurts"
|
| 1742 |
+
}
|
pred.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
pred_str=['三 頭 無 小 ', '三 頭 無 無 ', '三 頭 無 ', '三 頭 人 無 人 ', '大 人 無 ', '三 頭 一 人 ', '跤 頭 ', '三 頭 無 小 ', '大 坑 ', '大 湯 ', '三 頭 無 ', '跤 頭 ', '三 頭 仔 ', '烏 頭 ', '大 人 無 ', '跤 頭 ', '大 頭 仔 ', '三 頭 仔 ', '大 湲 ', '三 人 無 無 ', '大 人 人 人 人 人 ', '跤 仔 ', '大 人 無 無 ', '大 坑 ', '三 頭 仔 ', '跤 仔 ', '跤 頭 ', '三 頭 人 人 人 人 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 頭 ', '大 人 無 無 ', '大 湲 ', '大 頭 仔 ', '徘 ', '大 坑 ', '大 角 ', '三 頭 無 ', '大 人 人 人 人 人 ', '大 湯 ', '大 湲 ', '三 頭 頭 ', '大 人 無 ', '大 大 路 ', '大 大 路 ', '大 坑 ', '三 頭 仔 ', '跤 仔 ', '三 頭 無 小 ', '大 角 仔 ', '跤 頭 ', '大 坵 ', '雞 仔 仔 ', '鵾 仔 ', '大 大 路 ', '大 人 人 人 人 ', '三 頭 頭 ', '三 頭 仔 ', '三 頭 無 ', '大 人 無 ', '大 磾 ', '跤 仔 ', '跤 頭 ', '三 人 無 無 人 ', '三 頭 仔 ', '跤 仔 ', '大 人 無 無 ', '大 人 人 人 人 ', '大 火 ', '大 磾 ', '大 頭 仔 ', '大 磾 ', '大 坑 ', '大 湲 ', '大 坵 ', '大 人 無 ', '大 大 路 ', '大 湲 ', '大 人 無 ', '大 人 人 人 ', '三 頭 仔 ', '大 人 無 ', '跤 ', '三 頭 無 無 ', '大 頭 仔 ', '跤 仔 ', '跤 頭 ', '三 頭 無 人 ', '鵭 仔 ', '大 頭 仔 ', '烏 頭 ', '三 頭 頭 ', '跤 仔 ', '大 磾 ', '三 頭 無 無 ', '三 頭 無 無 ', '三 頭 人 人 人 ', '三 人 人 人 一 人 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 頭 仔 ', '跤 頭 ', '大 大 路 ', '大 頭 ', '跤 仔 ', '跤 頭 ', '跤 仔 ', '鵭 仔 ', '跤 頭 ', '雞 頭 ', '跤 仔 ', '三 頭 頭 ', '跤 仔 ', '大 湯 ', '跤 仔 ', '三 頭 人 人 一 生 一 生 ', '三 頭 無 小 ', '大 爯 ', '大 湲 ', '大 人 人 人 人 ', '三 頭 頭 ', '大 人 無 ', '三 頭 無 無 ', '三 頭 頭 ', '大 人 無 ', '三 人 無 人 ', '大 大 路 ', '三 頭 無 無 ', '大 頭 仔 ', '大 人 無 ', '大 坵 ', '大 人 無 人 ', '大 人 無 ', '大 人 人 人 人 ', '大 頭 仔 ', '大 湯 ', '跤 頭 ', '大 湯 ', '大 坵 ', '跤 仔 ', '大 坑 ', '三 頭 人 人 生 生 一 生 ', '三 人 人 人 人 人 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 人 人 人 ', '大 大 路 ', '三 頭 無 無 ', '大 坑 ', '大 頭 仔 ', '大 人 無 ', '大 大 路 ', '三 頭 無 小 ', '三 頭 人 一 人 一 生 一 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 人 無 ', '大 人 無 ', '大 人 人 人 人 ', '大 人 無 無 ', '大 人 人 人 人 人 ', '大 坵 ', '大 坑 ', '大 人 無 ', '大 大 路 ', '大 坵 ', '大 人 無 無 ', '大 人 無 無 ', '大 人 人 人 ', '大 人 人 人 ', '大 坵 ', '大 大 路 ', '大 湯 ', '三 頭 無 小 ', '大 人 無 無 ', '跤 仔 ', '大 坵 仔 ', '三 頭 無 人 ', '大 人 無 ', '三 頭 人 一 人 生 生 ', '大 坵 ', '大 人 無 ', '三 頭 無 無 ', '三 頭 頭 ', '跤 仔 ', '三 頭 人 人 生 生 生 ', '三 頭 無 小 ', '這 人 人 人 人 人 人 人 人 伊 人 伊 人 伊 人 伊 人 伊 人 伊 人 ', '大 湯 ', '大 人 無 ', '大 人 無 ', '大 火 ', '跤 仔 ', '大 湲 ', '跤 仔 ', '大 湲 ', '鵭 仔 ', '徘 ', '大 坑 ', '大 坑 ', '大 磾 ', '大 湯 ', '大 人 無 ', '大 人 人 人 人 ', '大 火 ', '三 人 無 無 ', '三 人 人 人 人 人 人 人 人 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '三 頭 人 人 一 人 ', '三 頭 人 人 一 人 ', '三 頭 人 人 一 人 ', '三 頭 人 人 一 生 生 ', '三 人 無 無 ', '三 頭 人 人 生 生 一 生 ', '大 人 無 無 ', '大 人 無 無 ', '大 人 人 人 ', '大 人 人 人 人 ', '三 頭 無 人 ', '大 頭 無 ', '三 頭 人 人 人 人 ', '大 人 無 無 ', '三 頭 無 ', '三 頭 無 無 ', '跤 仔 ', '三 頭 無 小 ', '跤 頭 ', '三 頭 無 小 ', '跤 仔 ', '三 頭 無 小 ', '跤 頭 ', '三 頭 無 小 ', '三 頭 無 小 ', '跤 仔 ', '跤 仔 ', '三 頭 無 小 ', '跤 仔 ', '三 頭 無 小 ', '三 頭 頭 生 ', '三 頭 人 一 人 生 生 生 ', '跤 頭 ', '跤 頭 ', '跤 頭 ', '鵬 ', '雞 頭 ', '大 坵 ', '鵭 ', '跤 仔 ', '跤 頭 ', '大 湲 ', '鵾 仔 ', '跤 仔 ', '大 坑 ', '跤 頭 ', '大 坑 ', '大 磾 ', '三 頭 無 ', '跤 仔 ', '三 頭 無 ', '跤 頭 ', '鵭 ', '大 角 仔 ', '大 頭 仔 ', '大 角 ', '大 火 ', '三 頭 無 ', '三 頭 頭 ', '跤 仔 ', '三 頭 無 小 ', '雞 頭 ', '大 人 無 ', '大 火 仔 ', '大 人 無 ', '三 頭 仔 ', '大 頭 仔 ', '大 頭 仔 ', '大 人 無 ', '大 人 無 無 ', '大 坵 ', '三 頭 無 無 ', '三 頭 無 ', '跤 仔 ', '三 頭 人 一 人 生 生 一 生 頂 頂 頂 頂 頂 頂 頂 �� 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '三 頭 頭 ', '大 人 無 ', '三 頭 頭 ', '三 頭 人 人 一 生 一 生 ', '三 頭 人 人 ', '大 人 無 無 ', '三 頭 人 一 人 生 生 生 ', '大 人 無 無 ', '大 頭 無 無 ', '三 頭 頭 ', '三 頭 一 人 生 生 生 ', '鵭 仔 ', '三 頭 無 無 ', '大 湲 ', '大 頭 無 無 ', '跤 頭 ', '大 頭 ', '大 人 無 無 ', '三 頭 頭 ', '跤 頭 ', '三 頭 仔 ', '跤 仔 ', '三 頭 頭 ', '三 頭 頭 ', '大 湲 ', '跤 頭 ', '三 頭 頭 ', '三 頭 頭 ', '大 大 路 ', '跤 頭 ', '跤 仔 ', '三 頭 頭 ', '跤 仔 ', '跤 仔 ', '大 角 ', '三 頭 仔 ', '跤 頭 ', '跤 頭 ', '跤 頭 ', '跤 仔 ', '鵬 ', '大 湯 ', '大 人 無 ', '三 頭 人 人 生 生 生 ', '三 頭 無 無 ', '三 頭 無 小 ', '大 人 無 ', '大 人 無 ', '大 角 仔 ', '三 頭 無 無 ', '三 頭 仔 ', '大 頭 ', '三 頭 無 無 ', '大 湯 ', '這 人 人 人 人 人 人 人 人 人 人 ', '大 湯 ', '大 人 無 無 ', '大 大 路 ', '大 大 路 ', '大 湲 ', '這 人 人 人 人 人 人 人 人 人 伊 人 ', '跤 仔 ', '大 人 無 ', '大 人 人 人 人 ', '三 頭 人 人 一 人 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 人 無 ', '這 人 人 人 人 人 人 人 人 人 人 ', '大 人 無 ', '大 人 無 無 ', '大 湲 ', '大 人 無 ', '大 頭 仔 ', '大 人 無 ', '大 坵 ', '大 人 無 ', '大 人 無 ', '大 角 ', '大 大 路 ', '大 大 路 ', '大 大 路 ', '大 湲 ', '大 人 人 人 人 ', '跤 頭 ', '大 人 無 ', '大 人 無 ', '大 人 無 ', '大 人 人 人 ', '大 大 路 ', '大 大 路 ', '大 大 路 ', '大 人 無 ', '大 角 仔 ', '三 頭 人 人 人 人 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 人 人 人 人 ', '大 人 無 ', '大 人 無 ', '大 人 無 ', '大 湯 ', '大 人 無 無 ', '跤 仔 ', '三 頭 無 人 ', '三 頭 無 小 ', '三 頭 無 無 ', '大 頭 無 無 ', '三 頭 無 ', '大 人 無 ', '大 坑 ', '烏 頭 仔 ', '跤 仔 ', '三 頭 人 一 人 生 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '三 頭 仔 ', '跤 頭 ', '大 人 無 無 ', '雞 頭 ', '跤 頭 ', '三 頭 無 小 ', '大 人 人 人 人 人 ', '大 人 無 ', '大 頭 仔 ', '三 頭 人 一 人 生 生 生 一 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 人 無 ', '跤 仔 ', '三 頭 人 一 人 生 生 生 ', '跤 頭 ', '大 角 ', '鵭 仔 ', '大 人 無 ', '大 人 無 ', '跤 仔 ', '大 人 無 ', '鵬 ', '大 磾 ', '大 大 路 ', '大 磾 ', '大 坑 ', '大 磾 ', '大 人 無 ', '大 湯 ', '大 坵 ', '大 大 路 ', '大 大 路 ', '大 湯 ', '大 湲 ', '大 坵 ', '大 火 ', '大 大 路 ', '大 坑 ', '這 人 人 人 人 人 人 人 人 人 人 ', '大 磾 ', '鵭 仔 ', '大 坑 ', '鵬 ', '大 坑 ', '大 人 無 ', '大 火 ', '大 坑 ', '大 坵 ', '大 磾 ', '大 磾 ', '大 人 無 ', '鵭 ', '大 頭 仔 ', '鵾 仔 ', '跤 仔 ', '大 角 ', '三 頭 仔 ', '大 湯 ', '三 頭 仔 ', '大 人 無 ', '大 角 ', '大 角 ', '三 人 人 人 人 人 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 角 仔 ', '大 大 路 ', '大 大 路 ', '三 頭 仔 ', '大 人 無 無 ', '大 角 ', '大 角 ', '大 角 ', '大 坑 ', '大 坵 仔 ', '大 人 無 ', '大 頭 仔 ', '大 湯 ', '大 角 ', '大 湲 ', '大 人 無 ', '大 人 無 ', '大 人 無 ', '大 人 無 ', '大 大 路 ', '大 坵 ', '大 湲 ', '大 頭 仔 ', '大 頭 仔 ', '大 坵 ', '大 頭 ', '大 頭 仔 ', '三 人 人 人 一 人 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 大 路 ', '大 人 人 人 人 ', '大 人 無 ', '鵬 ', '大 坑 ', '大 人 無 ', '大 大 路 ', '大 大 路 ', '大 人 人 人 人 ', '這 人 人 人 人 人 人 人 人 人 人 伊 人 ', '大 火 ', '大 坑 ', '大 磾 ', '大 坑 ', '大 湯 ', '大 湲 ', '大 坵 ', '大 湯 ', '大 湲 ', '大 磾 ', '大 磾 ', '大 磾 ', '大 大 路 ', '大 坑 ', '大 人 無 無 ', '大 人 無 ', '大 坑 ', '大 湲 ', '大 湯 ', '大 磾 ', '大 坑 ', '大 坑 ', '大 大 路 ', '大 湯 ', '大 磾 ', '大 頭 ', '大 湯 ', '大 磾 ', '大 磾 ', '大 頭 仔 ', '大 人 無 ', '大 人 人 人 人 ', '三 頭 無 無 ', '大 頭 仔 ', '大 頭 仔 ', '三 頭 無 小 ', '大 頭 ', '大 人 無 無 ', '三 頭 一 人 ', '這 人 人 人 人 人 人 人 人 人 ', '大 頭 仔 ', '三 頭 無 無 ', '三 頭 無 小 ', '大 火 ', '三 頭 人 人 生 生 生 ', '三 頭 無 人 ', '大 人 人 人 人 ', '三 人 人 人 人 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '三 頭 無 無 ', '三 頭 一 人 生 一 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 坵 ', '大 人 無 ', '大 人 無 ', '大 人 人 人 人 ', '這 人 人 人 人 人 人 人 人 人 人 人 人 伊 人 伊 人 伊 人 ', '大 人 無 ', '三 人 無 無 ', '三 頭 無 小 ', '大 人 無 無 ', '大 火 ', '三 頭 仔 ', '三 頭 人 人 一 人 ', '三 頭 一 人 生 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '三 頭 無 人 ', '跤 頭 ', '三 頭 仔 ', '大 人 無 無 ', '這 人 人 人 人 人 人 人 人 人 人 伊 人 ', '三 頭 無 ', '大 人 無 ', '跤 頭 ', '三 頭 仔 ', '大 坵 ', '大 坑 ', '大 人 無 無 ', '大 坵 ', '徘 ', '大 坵 ', '大 湲 ', '大 湯 ', '大 人 無 ', '跤 仔 ', '大 大 路 ', '大 坵 仔 ', '三 頭 人 無 人 ', '大 坵 ', '大 大 路 ', '大 人 無 ', '大 坵 仔 ', '徘 ', '大 大 路 ', '大 坑 ', '大 坑 ', '大 人 無 ', '大 湯 ', '大 大 路 ', '三 頭 無 無 ', '大 大 路 ', '大 湲 ', '大 坑 ', '大 人 無 ', '大 坑 ', '大 大 路 ', '大 湲 ', '大 坑 ', '大 坵 ', '大 坑 ', '大 坵 ', '大 大 路 ', '大 坵 ', '大 火 ', '大 人 無 ', '大 人 人 人 人 ', '大 湯 ', '大 人 無 ', '大 大 路 ', '大 坵 仔 ', '三 頭 無 小 ', '跤 仔 ', '大 人 無 ', '三 頭 無 小 ', '三 頭 人 人 人 生 生 一 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 坑 ', '鵬 ', '大 坑 ', '三 頭 無 小 ', '大 人 無 無 ', '三 頭 無 ', '跤 仔 ', '跤 頭 ', '大 湲 ', '三 頭 仔 ', '跤 仔 ', '跤 仔 ', '跤 頭 ', '三 頭 無 無 ', '跤 仔 ', '大 人 無 ', '大 爯 ', '大 湲 ', '大 坑 ', '大 人 人 人 人 ', '三 頭 無 小 ', '三 頭 無 ', '大 坑 ', '跤 頭 ', '三 頭 無 ', '大 角 ', '大 湯 ', '大 人 無 ', '大 人 無 無 ', '大 人 無 ', '大 坑 ', '大 坵 ', '大 人 無 ', '三 頭 無 ', '三 頭 無 ', '大 坑 ', '跤 仔 ', '跤 頭 ', '跤 仔 ', '大 頭 仔 ', '三 頭 頭 ', '大 頭 ', '跤 仔 ', '三 頭 頭 ', '大 火 ', '三 頭 無 小 ', '跤 頭 ', '三 人 無 無 無 ', '大 人 無 人 ', '大 人 無 ', '鵬 ', '跤 仔 ', '大 火 ', '鵭 仔 ', '大 頭 仔 ', '跤 頭 ', '三 頭 人 人 一 生 一 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 人 無 無 ', '大 頭 仔 ', '鵭 仔 ', '大 人 無 ', '大 人 無 無 ', '雞 頭 ', '鵾 仔 ', '大 角 ', '大 磾 ', '三 頭 仔 ', '跤 頭 ', '三 頭 仔 ', '大 角 仔 ', '三 頭 仔 ', '大 人 無 ', '大 人 無 ', '鵭 仔 ', '跤 仔 ', '三 頭 無 ', '烏 頭 ', '三 頭 仔 ', '三 頭 人 人 一 人 ', '三 頭 仔 ', '跤 頭 ', '跤 仔 ', '三 頭 無 無 ', '三 頭 人 無 人 ', '大 人 無 ', '跤 仔 ', '三 頭 無 小 ', '大 頭 仔 ', '三 頭 無 ', '大 頭 仔 ', '三 頭 人 一 人 生 生 生 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 頭 仔 ', '三 頭 無 無 ', '跤 仔 ', '大 火 ', '大 磾 ', '大 磾 ', '大 人 無 ', '鵬 ', '跤 仔 ', '跤 頭 ', '鵭 仔 ', '跤 仔 ', '大 人 無 ', '大 人 無 ', '大 頭 路 ', '大 人 無 ', '雞 頭 ', '大 坑 ', '大 坑 ', '大 人 無 無 ', '大 人 無 ', '三 頭 無 小 ', '徘 ', '大 坑 ', '大 磾 ', '鵭 仔 ', '大 人 無 無 ', '大 湲 ', '大 火 ', '大 人 無 ', '大 人 人 人 ', '大 大 路 ', '大 坑 ', '大 角 仔 ', '大 人 人 人 ', '大 磾 ', '大 爯 ', '大 磾 ', '大 人 人 人 人 ', '大 磾 ', '大 人 無 ', '大 人 無 無 ', '大 湯 ', '大 磾 ', '大 火 ', '大 湲 ', '大 湲 ', '大 湲 ', '大 爯 ', '大 坑 ', '徘 ', '徘 ', '大 坑 ', '大 坑 ', '大 磾 ', '徘 ', '大 人 無 ', '大 人 無 ', '大 坑 ', '大 坵 ', '徘 ', '大 坑 ', '大 坵 ', '大 大 路 ', '鵬 ', '跤 仔 ', '徘 ', '大 大 路 ', '大 大 路 ', '大 人 無 ', '大 坑 ', '大 坑 ', '大 人 無 ', '大 人 無 ', '大 湲 ', '大 大 路 ', '三 頭 無 無 ', '三 頭 無 小 ', '跤 仔 ', '大 坑 ', '大 人 無 ', '三 頭 人 一 人 生 生 生 ', '大 人 無 無 ', '三 頭 無 ', '大 頭 仔 ', '大 湲 ', '大 人 無 無 ', '大 人 無 ', '大 人 無 ', '三 頭 無 ', '大 人 人 人 人 ', '三 頭 一 人 ', '三 頭 人 一 人 生 生 ', '跤 仔 ', '大 人 無 ', '三 頭 一 人 ', '三 人 無 人 ', '跤 仔 ', '大 人 無 無 ', '三 頭 人 人 一 生 生 生 ', '大 頭 仔 ', '三 頭 頭 ', '大 頭 ', '大 人 人 人 人 ', '大 湲 ', '大 人 無 ', '大 角 ', '大 人 人 人 ', '三 頭 無 小 ', '三 頭 頭 生 ', '大 人 無 ', '大 人 無 ', '大 人 人 人 人 ', '大 人 人 人 ', '三 頭 仔 ', '大 人 人 人 ', '三 頭 人 人 一 人 ', '三 頭 仔 ', '三 頭 無 小 ', '大 頭 ', '大 人 無 無 ', '大 坵 ', '三 頭 無 人 ', '大 磾 ', '大 火 仔 ', '大 湲 ', '跤 頭 ', '跤 頭 ', '三 頭 頭 ', '三 頭 無 無 ', '三 頭 無 無 ', '三 頭 無 生 ', '三 頭 仔 ', '三 頭 人 一 人 生 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '三 頭 仔 ', '大 人 無 ', '大 大 路 ', '大 人 無 ', '烏 頭 仔 ', '大 人 無 無 ', '大 人 無 ', '大 人 無 ', '大 人 無 ', '大 湯 ', '跤 頭 ', '大 頭 無 ', '三 人 人 人 人 人 人 人 人 人 人 一 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '三 人 無 人 ', '大 頭 ', '大 火 ', '跤 頭 ', '大 人 無 ', '鵾 仔 ', '跤 仔 ', '三 頭 無 無 ', '大 人 無 無 ', '大 大 路 ', '三 頭 仔 ', '大 湲 ', '大 湯 ', '大 湲 ', '大 磾 ', '跤 仔 ', '大 人 無 ', '大 火 仔 ', '大 頭 仔 ', '三 頭 頭 ', '鵬 ', '大 人 無 ', '大 人 無 ', '大 人 無 ', '大 人 無 ', '大 湲 ', '跤 頭 ', '跤 頭 ', '三 頭 無 無 ', '大 大 路 ', '大 坵 ', '鵭 仔 ', '大 人 無 無 ', '大 人 無 ', '三 頭 無 小 ', '大 火 ', '大 大 路 ', '大 頭 ', '鵭 ', '大 大 路 ', '大 磾 ', '跤 仔 ', '大 大 路 ', '大 人 無 ', '大 人 無 ', '大 火 ', '大 人 無 ', '大 頭 仔 ', '大 湯 ', '大 磾 ', '大 磾 ', '大 磾 ', '大 湲 ', '大 湯 ', '大 湲 ', '大 人 無 ', '大 湯 ', '大 人 無 ', '大 湯 ', '大 人 人 人 人 人 ', '大 磾 ', '大 湲 ', '大 人 無 ', '大 磾 ', '大 磾 ', '大 人 無 ', '大 湲 ', '大 湲 ', '大 人 無 ', '大 人 無 ', '大 大 路 ', '大 人 人 人 ', '大 人 無 ', '大 人 無 無 ', '大 人 無 無 ', '大 湲 ', '大 人 人 人 人 人 ', '大 人 無 ', '大 大 路 ', '大 人 無 ', '大 人 人 人 人 ', '大 人 無 ', '大 人 無 ', '大 人 無 ', '大 人 無 ', '大 人 人 人 人 ', '大 人 無 無 ', '大 湯 ', '大 湯 ', '大 人 無 ', '大 人 無 ', '大 大 路 ', '大 人 無 ', '三 頭 無 ', '大 湲 ', '大 火 ', '大 頭 仔 ', '大 人 無 ', '大 人 無 ', '三 頭 人 人 一 人 生 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 頂 ', '大 湲 ', '大 湲 ', '大 湲 ', '大 湯 ', '大 坑 ', '跤 仔 ', '大 人 無 ', '大 人 無 ', '大 磾 ', '大 大 路 ', '鵭 仔 ', '大 磾 ', '跤 仔 ', '大 湲 ', '三 頭 無 無 ', '大 大 路 ', '大 人 人 人 人 ', '大 人 無 ', '大 人 無 ', '大 火 ', '三 頭 人 人 ', '大 湲 ', '大 大 路 ', '大 人 無 ', '大 頭 仔 ', '大 坵 ', '大 坑 ', '大 人 無 無 ', '大 湲 ', '大 人 無 ', '大 人 無 ', '大 湯 ', '大 人 無 ', '大 火 ', '大 湲 ', '大 人 無 ', '大 磾 ', '大 人 無 ', '大 人 無 ', '大 人 無 ', '大 湲 ', '大 湯 ']
|
preprocessor_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c1e1cf1e0f592d5e4a409fb4bad5c85a3999010e244b51f776a67a2fc6c0616
|
| 3 |
+
size 6173655480
|
run.sh
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
python3 run_speech_recognition_seq2seq_streaming.py \
|
| 2 |
+
--model_name_or_path="openai/whisper-large-v2" \
|
| 3 |
+
--dataset_name="mozilla-foundation/common_voice_11_0" \
|
| 4 |
+
--dataset_config_name="nan-tw" \
|
| 5 |
+
--language="chinese" \
|
| 6 |
+
--train_split_name="train" \
|
| 7 |
+
--eval_split_name="test" \
|
| 8 |
+
--model_index_name="Whisper large-v2 nan-tw" \
|
| 9 |
+
--max_steps="5000" \
|
| 10 |
+
--output_dir="./" \
|
| 11 |
+
--per_device_train_batch_size="2" \
|
| 12 |
+
--per_device_eval_batch_size="2" \
|
| 13 |
+
--logging_steps="25" \
|
| 14 |
+
--learning_rate="1e-5" \
|
| 15 |
+
--warmup_steps="500" \
|
| 16 |
+
--evaluation_strategy="steps" \
|
| 17 |
+
--eval_steps="1000" \
|
| 18 |
+
--save_strategy="steps" \
|
| 19 |
+
--save_steps="1000" \
|
| 20 |
+
--generation_max_length="225" \
|
| 21 |
+
--length_column_name="input_length" \
|
| 22 |
+
--max_duration_in_seconds="30" \
|
| 23 |
+
--text_column_name="sentence" \
|
| 24 |
+
--freeze_feature_encoder="False" \
|
| 25 |
+
--report_to="tensorboard" \
|
| 26 |
+
--gradient_checkpointing \
|
| 27 |
+
--fp16 \
|
| 28 |
+
--overwrite_output_dir \
|
| 29 |
+
--do_train \
|
| 30 |
+
--do_eval \
|
| 31 |
+
--predict_with_generate \
|
| 32 |
+
--do_normalize_eval \
|
| 33 |
+
--use_auth_token \
|
| 34 |
+
--optim="adamw_bnb_8bit"
|
run_speech_recognition_seq2seq_streaming.py
ADDED
|
@@ -0,0 +1,617 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
# coding=utf-8
|
| 3 |
+
# Copyright 2022 The HuggingFace Team. All rights reserved.
|
| 4 |
+
#
|
| 5 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
| 6 |
+
# you may not use this file except in compliance with the License.
|
| 7 |
+
# You may obtain a copy of the License at
|
| 8 |
+
#
|
| 9 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
| 10 |
+
#
|
| 11 |
+
# Unless required by applicable law or agreed to in writing, software
|
| 12 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
| 13 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 14 |
+
# See the License for the specific language governing permissions and
|
| 15 |
+
# limitations under the License.
|
| 16 |
+
"""
|
| 17 |
+
Fine-tuning the library models for sequence to sequence speech recognition
|
| 18 |
+
with 🤗 Datasets' streaming mode.
|
| 19 |
+
"""
|
| 20 |
+
# You can also adapt this script for your own sequence to sequence speech
|
| 21 |
+
# recognition task. Pointers for this are left as comments.
|
| 22 |
+
import ryNormText
|
| 23 |
+
import logging
|
| 24 |
+
import os
|
| 25 |
+
import re
|
| 26 |
+
import string
|
| 27 |
+
import sys
|
| 28 |
+
from dataclasses import dataclass, field
|
| 29 |
+
from typing import Any, Dict, List, Optional, Union
|
| 30 |
+
|
| 31 |
+
import datasets
|
| 32 |
+
import torch
|
| 33 |
+
from datasets import IterableDatasetDict, interleave_datasets, load_dataset
|
| 34 |
+
from torch.utils.data import IterableDataset
|
| 35 |
+
|
| 36 |
+
import evaluate
|
| 37 |
+
import transformers
|
| 38 |
+
from transformers import (
|
| 39 |
+
AutoConfig,
|
| 40 |
+
AutoFeatureExtractor,
|
| 41 |
+
AutoModelForSpeechSeq2Seq,
|
| 42 |
+
AutoProcessor,
|
| 43 |
+
AutoTokenizer,
|
| 44 |
+
HfArgumentParser,
|
| 45 |
+
Seq2SeqTrainer,
|
| 46 |
+
Seq2SeqTrainingArguments,
|
| 47 |
+
TrainerCallback,
|
| 48 |
+
set_seed,
|
| 49 |
+
)
|
| 50 |
+
from transformers.trainer_pt_utils import IterableDatasetShard
|
| 51 |
+
from transformers.trainer_utils import get_last_checkpoint, is_main_process
|
| 52 |
+
from transformers.utils import check_min_version, send_example_telemetry
|
| 53 |
+
from transformers.utils.versions import require_version
|
| 54 |
+
|
| 55 |
+
# Will error if the minimal version of Transformers is not installed. Remove at your own risks.
|
| 56 |
+
check_min_version("4.25.0.dev0")
|
| 57 |
+
|
| 58 |
+
require_version("datasets>=1.18.2", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
|
| 59 |
+
|
| 60 |
+
logger = logging.getLogger(__name__)
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
@dataclass
|
| 64 |
+
class ModelArguments:
|
| 65 |
+
"""
|
| 66 |
+
Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
|
| 67 |
+
"""
|
| 68 |
+
|
| 69 |
+
model_name_or_path: str = field(
|
| 70 |
+
metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"}
|
| 71 |
+
)
|
| 72 |
+
config_name: Optional[str] = field(
|
| 73 |
+
default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
|
| 74 |
+
)
|
| 75 |
+
tokenizer_name: Optional[str] = field(
|
| 76 |
+
default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
|
| 77 |
+
)
|
| 78 |
+
feature_extractor_name: Optional[str] = field(
|
| 79 |
+
default=None, metadata={"help": "feature extractor name or path if not the same as model_name"}
|
| 80 |
+
)
|
| 81 |
+
cache_dir: Optional[str] = field(
|
| 82 |
+
default=None,
|
| 83 |
+
metadata={"help": "Where to store the pretrained models downloaded from huggingface.co"},
|
| 84 |
+
)
|
| 85 |
+
use_fast_tokenizer: bool = field(
|
| 86 |
+
default=True,
|
| 87 |
+
metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
|
| 88 |
+
)
|
| 89 |
+
model_revision: str = field(
|
| 90 |
+
default="main",
|
| 91 |
+
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
|
| 92 |
+
)
|
| 93 |
+
use_auth_token: bool = field(
|
| 94 |
+
default=False,
|
| 95 |
+
metadata={
|
| 96 |
+
"help": (
|
| 97 |
+
"Will use the token generated when running `huggingface-cli login` (necessary to use this script "
|
| 98 |
+
"with private models)."
|
| 99 |
+
)
|
| 100 |
+
},
|
| 101 |
+
)
|
| 102 |
+
freeze_feature_encoder: bool = field(
|
| 103 |
+
default=True, metadata={"help": "Whether to freeze the feature encoder layers of the model."}
|
| 104 |
+
)
|
| 105 |
+
freeze_encoder: bool = field(
|
| 106 |
+
default=False, metadata={"help": "Whether to freeze the entire encoder of the seq2seq model."}
|
| 107 |
+
)
|
| 108 |
+
forced_decoder_ids: List[List[int]] = field(
|
| 109 |
+
default=None,
|
| 110 |
+
metadata={
|
| 111 |
+
"help": (
|
| 112 |
+
"A list of pairs of integers which indicates a mapping from generation indices to token indices "
|
| 113 |
+
"that will be forced before sampling. For example, [[0, 123]] means the first generated token "
|
| 114 |
+
"will always be a token of index 123."
|
| 115 |
+
)
|
| 116 |
+
},
|
| 117 |
+
)
|
| 118 |
+
suppress_tokens: List[int] = field(
|
| 119 |
+
default=None, metadata={"help": "A list of tokens that will be suppressed at generation."}
|
| 120 |
+
)
|
| 121 |
+
model_index_name: str = field(default=None, metadata={"help": "Pretty name for the model card."})
|
| 122 |
+
|
| 123 |
+
|
| 124 |
+
@dataclass
|
| 125 |
+
class DataTrainingArguments:
|
| 126 |
+
"""
|
| 127 |
+
Arguments pertaining to what data we are going to input our model for training and eval.
|
| 128 |
+
"""
|
| 129 |
+
|
| 130 |
+
dataset_name: str = field(
|
| 131 |
+
default=None, metadata={"help": "The name of the dataset to use (via the datasets library)."}
|
| 132 |
+
)
|
| 133 |
+
dataset_config_name: Optional[str] = field(
|
| 134 |
+
default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
|
| 135 |
+
)
|
| 136 |
+
text_column: Optional[str] = field(
|
| 137 |
+
default=None,
|
| 138 |
+
metadata={"help": "The name of the column in the datasets containing the full texts (for summarization)."},
|
| 139 |
+
)
|
| 140 |
+
max_train_samples: Optional[int] = field(
|
| 141 |
+
default=None,
|
| 142 |
+
metadata={
|
| 143 |
+
"help": (
|
| 144 |
+
"For debugging purposes or quicker training, truncate the number of training examples to this "
|
| 145 |
+
"value if set."
|
| 146 |
+
)
|
| 147 |
+
},
|
| 148 |
+
)
|
| 149 |
+
max_eval_samples: Optional[int] = field(
|
| 150 |
+
default=None,
|
| 151 |
+
metadata={
|
| 152 |
+
"help": (
|
| 153 |
+
"For debugging purposes or quicker training, truncate the number of evaluation examples to this "
|
| 154 |
+
"value if set."
|
| 155 |
+
)
|
| 156 |
+
},
|
| 157 |
+
)
|
| 158 |
+
audio_column_name: str = field(
|
| 159 |
+
default="audio",
|
| 160 |
+
metadata={"help": "The name of the dataset column containing the audio data. Defaults to 'audio'"},
|
| 161 |
+
)
|
| 162 |
+
text_column_name: str = field(
|
| 163 |
+
default="text",
|
| 164 |
+
metadata={"help": "The name of the dataset column containing the text data. Defaults to 'text'"},
|
| 165 |
+
)
|
| 166 |
+
max_duration_in_seconds: float = field(
|
| 167 |
+
default=20.0,
|
| 168 |
+
metadata={
|
| 169 |
+
"help": (
|
| 170 |
+
"Truncate audio files that are longer than `max_duration_in_seconds` seconds to"
|
| 171 |
+
" 'max_duration_in_seconds`"
|
| 172 |
+
)
|
| 173 |
+
},
|
| 174 |
+
)
|
| 175 |
+
min_duration_in_seconds: float = field(
|
| 176 |
+
default=0.0, metadata={"help": "Filter audio files that are shorter than `min_duration_in_seconds` seconds"}
|
| 177 |
+
)
|
| 178 |
+
train_split_name: str = field(
|
| 179 |
+
default="train",
|
| 180 |
+
metadata={
|
| 181 |
+
"help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
|
| 182 |
+
},
|
| 183 |
+
)
|
| 184 |
+
eval_split_name: str = field(
|
| 185 |
+
default="test",
|
| 186 |
+
metadata={
|
| 187 |
+
"help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
|
| 188 |
+
},
|
| 189 |
+
)
|
| 190 |
+
do_lower_case: bool = field(
|
| 191 |
+
default=False,
|
| 192 |
+
metadata={"help": "Whether the target text should be lower cased."},
|
| 193 |
+
)
|
| 194 |
+
do_remove_punctuation: bool = field(
|
| 195 |
+
default=False,
|
| 196 |
+
metadata={"help": "Whether the target text should be striped of punctuation."},
|
| 197 |
+
)
|
| 198 |
+
do_normalize_eval: bool = field(
|
| 199 |
+
default=True,
|
| 200 |
+
metadata={"help": "Whether to normalise the references and predictions in the eval WER calculation."},
|
| 201 |
+
)
|
| 202 |
+
language: str = field(
|
| 203 |
+
default=None,
|
| 204 |
+
metadata={
|
| 205 |
+
"help": (
|
| 206 |
+
"Language for multilingual fine-tuning. This argument should be set for multilingual fine-tuning "
|
| 207 |
+
"only. For English speech recognition, it should be set to `None`."
|
| 208 |
+
)
|
| 209 |
+
},
|
| 210 |
+
)
|
| 211 |
+
task: str = field(
|
| 212 |
+
default="transcribe",
|
| 213 |
+
metadata={"help": "Task, either `transcribe` for speech recognition or `translate` for speech translation."},
|
| 214 |
+
)
|
| 215 |
+
shuffle_buffer_size: Optional[int] = field(
|
| 216 |
+
default=500,
|
| 217 |
+
metadata={
|
| 218 |
+
"help": (
|
| 219 |
+
"The number of streamed examples to download before shuffling them. The large the buffer, "
|
| 220 |
+
"the closer it is to real offline shuffling."
|
| 221 |
+
)
|
| 222 |
+
},
|
| 223 |
+
)
|
| 224 |
+
|
| 225 |
+
|
| 226 |
+
@dataclass
|
| 227 |
+
class DataCollatorSpeechSeq2SeqWithPadding:
|
| 228 |
+
"""
|
| 229 |
+
Data collator that will dynamically pad the inputs received.
|
| 230 |
+
Args:
|
| 231 |
+
processor ([`WhisperProcessor`])
|
| 232 |
+
The processor used for processing the data.
|
| 233 |
+
decoder_start_token_id (`int`)
|
| 234 |
+
The begin-of-sentence of the decoder.
|
| 235 |
+
"""
|
| 236 |
+
|
| 237 |
+
processor: Any
|
| 238 |
+
decoder_start_token_id: int
|
| 239 |
+
|
| 240 |
+
def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
|
| 241 |
+
# split inputs and labels since they have to be of different lengths and need
|
| 242 |
+
# different padding methods
|
| 243 |
+
model_input_name = self.processor.model_input_names[0]
|
| 244 |
+
input_features = [{model_input_name: feature[model_input_name]} for feature in features]
|
| 245 |
+
label_features = [{"input_ids": feature["labels"]} for feature in features]
|
| 246 |
+
|
| 247 |
+
batch = self.processor.feature_extractor.pad(input_features, return_tensors="pt")
|
| 248 |
+
|
| 249 |
+
labels_batch = self.processor.tokenizer.pad(label_features, return_tensors="pt")
|
| 250 |
+
|
| 251 |
+
# replace padding with -100 to ignore loss correctly
|
| 252 |
+
labels = labels_batch["input_ids"].masked_fill(labels_batch.attention_mask.ne(1), -100)
|
| 253 |
+
|
| 254 |
+
# if bos token is appended in previous tokenization step,
|
| 255 |
+
# cut bos token here as it's append later anyways
|
| 256 |
+
if (labels[:, 0] == self.decoder_start_token_id).all().cpu().item():
|
| 257 |
+
labels = labels[:, 1:]
|
| 258 |
+
|
| 259 |
+
batch["labels"] = labels
|
| 260 |
+
|
| 261 |
+
return batch
|
| 262 |
+
|
| 263 |
+
|
| 264 |
+
def load_streaming_dataset(dataset_name, dataset_config_name, split="train", **kwargs):
|
| 265 |
+
"""
|
| 266 |
+
Utility function to load a dataset in streaming mode. For datasets with multiple splits,
|
| 267 |
+
each split is loaded individually and then splits combined by taking alternating examples from
|
| 268 |
+
each (interleaving).
|
| 269 |
+
"""
|
| 270 |
+
if "+" in split:
|
| 271 |
+
# load multiple splits separated by the `+` symbol with streaming mode
|
| 272 |
+
dataset_splits = [
|
| 273 |
+
load_dataset(dataset_name, dataset_config_name, split=split_name, streaming=True, **kwargs)
|
| 274 |
+
for split_name in split.split("+")
|
| 275 |
+
]
|
| 276 |
+
# interleave multiple splits to form one dataset
|
| 277 |
+
interleaved_dataset = interleave_datasets(dataset_splits)
|
| 278 |
+
return interleaved_dataset
|
| 279 |
+
else:
|
| 280 |
+
# load a single split *with* streaming mode
|
| 281 |
+
dataset = load_dataset(dataset_name, dataset_config_name, split=split, streaming=True, **kwargs)
|
| 282 |
+
return dataset
|
| 283 |
+
|
| 284 |
+
|
| 285 |
+
def main():
|
| 286 |
+
# 1. Parse input arguments
|
| 287 |
+
# See all possible arguments in src/transformers/training_args.py
|
| 288 |
+
# or by passing the --help flag to this script.
|
| 289 |
+
# We now keep distinct sets of args, for a cleaner separation of concerns.
|
| 290 |
+
parser = HfArgumentParser((ModelArguments, DataTrainingArguments, Seq2SeqTrainingArguments))
|
| 291 |
+
|
| 292 |
+
if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
|
| 293 |
+
# If we pass only one argument to the script and it's the path to a json file,
|
| 294 |
+
# let's parse it to get our arguments.
|
| 295 |
+
model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
|
| 296 |
+
else:
|
| 297 |
+
model_args, data_args, training_args = parser.parse_args_into_dataclasses()
|
| 298 |
+
|
| 299 |
+
# Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
|
| 300 |
+
# information sent is the one passed as arguments along with your Python/PyTorch versions.
|
| 301 |
+
send_example_telemetry("run_speech_recognition_seq2seq_streaming", model_args, data_args)
|
| 302 |
+
|
| 303 |
+
# 2. Setup logging
|
| 304 |
+
logging.basicConfig(
|
| 305 |
+
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
|
| 306 |
+
datefmt="%m/%d/%Y %H:%M:%S",
|
| 307 |
+
handlers=[logging.StreamHandler(sys.stdout)],
|
| 308 |
+
)
|
| 309 |
+
log_level = training_args.get_process_log_level()
|
| 310 |
+
logger.setLevel(log_level)
|
| 311 |
+
datasets.utils.logging.set_verbosity(log_level)
|
| 312 |
+
transformers.utils.logging.set_verbosity(log_level)
|
| 313 |
+
transformers.utils.logging.enable_default_handler()
|
| 314 |
+
transformers.utils.logging.enable_explicit_format()
|
| 315 |
+
|
| 316 |
+
logger.setLevel(logging.INFO if is_main_process(training_args.local_rank) else logging.WARN)
|
| 317 |
+
|
| 318 |
+
# Log on each process the small summary:
|
| 319 |
+
logger.warning(
|
| 320 |
+
f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
|
| 321 |
+
f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
|
| 322 |
+
)
|
| 323 |
+
logger.info(f"Training/evaluation parameters {training_args}")
|
| 324 |
+
|
| 325 |
+
# Set the verbosity to info of the Transformers logger (on main process only):
|
| 326 |
+
if is_main_process(training_args.local_rank):
|
| 327 |
+
transformers.utils.logging.set_verbosity_info()
|
| 328 |
+
logger.info("Training/evaluation parameters %s", training_args)
|
| 329 |
+
|
| 330 |
+
# 3. Detecting last checkpoint and eventually continue from last checkpoint
|
| 331 |
+
last_checkpoint = None
|
| 332 |
+
if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
|
| 333 |
+
last_checkpoint = get_last_checkpoint(training_args.output_dir)
|
| 334 |
+
if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
|
| 335 |
+
raise ValueError(
|
| 336 |
+
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
|
| 337 |
+
"Use --overwrite_output_dir to overcome."
|
| 338 |
+
)
|
| 339 |
+
elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
|
| 340 |
+
logger.info(
|
| 341 |
+
f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
|
| 342 |
+
"the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
|
| 343 |
+
)
|
| 344 |
+
|
| 345 |
+
# Set seed before initializing model.
|
| 346 |
+
set_seed(training_args.seed)
|
| 347 |
+
|
| 348 |
+
# 4. Load dataset
|
| 349 |
+
raw_datasets = IterableDatasetDict()
|
| 350 |
+
|
| 351 |
+
if training_args.do_train:
|
| 352 |
+
raw_datasets["train"] = load_streaming_dataset(
|
| 353 |
+
data_args.dataset_name,
|
| 354 |
+
data_args.dataset_config_name,
|
| 355 |
+
split=data_args.train_split_name,
|
| 356 |
+
use_auth_token=True if model_args.use_auth_token else None,
|
| 357 |
+
)
|
| 358 |
+
|
| 359 |
+
if training_args.do_eval:
|
| 360 |
+
raw_datasets["eval"] = load_streaming_dataset(
|
| 361 |
+
data_args.dataset_name,
|
| 362 |
+
data_args.dataset_config_name,
|
| 363 |
+
split=data_args.eval_split_name,
|
| 364 |
+
use_auth_token=True if model_args.use_auth_token else None,
|
| 365 |
+
)
|
| 366 |
+
|
| 367 |
+
raw_datasets_features = list(next(iter(raw_datasets.values())).features.keys())
|
| 368 |
+
|
| 369 |
+
if data_args.audio_column_name not in raw_datasets_features:
|
| 370 |
+
raise ValueError(
|
| 371 |
+
f"--audio_column_name '{data_args.audio_column_name}' not found in dataset '{data_args.dataset_name}'. "
|
| 372 |
+
"Make sure to set `--audio_column_name` to the correct audio column - one of "
|
| 373 |
+
f"{', '.join(raw_datasets_features)}."
|
| 374 |
+
)
|
| 375 |
+
|
| 376 |
+
if data_args.text_column_name not in raw_datasets_features:
|
| 377 |
+
raise ValueError(
|
| 378 |
+
f"--text_column_name {data_args.text_column_name} not found in dataset '{data_args.dataset_name}'. "
|
| 379 |
+
"Make sure to set `--text_column_name` to the correct text column - one of "
|
| 380 |
+
f"{', '.join(raw_datasets_features)}."
|
| 381 |
+
)
|
| 382 |
+
|
| 383 |
+
# 5. Load pretrained model, tokenizer, and feature extractor
|
| 384 |
+
#
|
| 385 |
+
# Distributed training:
|
| 386 |
+
# The .from_pretrained methods guarantee that only one local process can concurrently
|
| 387 |
+
config = AutoConfig.from_pretrained(
|
| 388 |
+
model_args.config_name if model_args.config_name else model_args.model_name_or_path,
|
| 389 |
+
cache_dir=model_args.cache_dir,
|
| 390 |
+
revision=model_args.model_revision,
|
| 391 |
+
use_auth_token=True if model_args.use_auth_token else None,
|
| 392 |
+
)
|
| 393 |
+
|
| 394 |
+
config.update({"forced_decoder_ids": model_args.forced_decoder_ids, "suppress_tokens": model_args.suppress_tokens})
|
| 395 |
+
|
| 396 |
+
feature_extractor = AutoFeatureExtractor.from_pretrained(
|
| 397 |
+
model_args.feature_extractor_name if model_args.feature_extractor_name else model_args.model_name_or_path,
|
| 398 |
+
cache_dir=model_args.cache_dir,
|
| 399 |
+
revision=model_args.model_revision,
|
| 400 |
+
use_auth_token=True if model_args.use_auth_token else None,
|
| 401 |
+
)
|
| 402 |
+
tokenizer = AutoTokenizer.from_pretrained(
|
| 403 |
+
model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
|
| 404 |
+
cache_dir=model_args.cache_dir,
|
| 405 |
+
use_fast=model_args.use_fast_tokenizer,
|
| 406 |
+
revision=model_args.model_revision,
|
| 407 |
+
use_auth_token=True if model_args.use_auth_token else None,
|
| 408 |
+
)
|
| 409 |
+
model = AutoModelForSpeechSeq2Seq.from_pretrained(
|
| 410 |
+
model_args.model_name_or_path,
|
| 411 |
+
config=config,
|
| 412 |
+
cache_dir=model_args.cache_dir,
|
| 413 |
+
revision=model_args.model_revision,
|
| 414 |
+
use_auth_token=True if model_args.use_auth_token else None,
|
| 415 |
+
)
|
| 416 |
+
|
| 417 |
+
if model.config.decoder_start_token_id is None:
|
| 418 |
+
raise ValueError("Make sure that `config.decoder_start_token_id` is correctly defined")
|
| 419 |
+
|
| 420 |
+
if model_args.freeze_feature_encoder:
|
| 421 |
+
model.freeze_feature_encoder()
|
| 422 |
+
|
| 423 |
+
if model_args.freeze_encoder:
|
| 424 |
+
model.freeze_encoder()
|
| 425 |
+
model.model.encoder.gradient_checkpointing = False
|
| 426 |
+
|
| 427 |
+
if data_args.language is not None:
|
| 428 |
+
# We only need to set the task id when the language is specified (i.e. in a multilingual setting)
|
| 429 |
+
tokenizer.set_prefix_tokens(language=data_args.language, task=data_args.task)
|
| 430 |
+
|
| 431 |
+
# 6. Resample speech dataset if necessary
|
| 432 |
+
dataset_sampling_rate = next(iter(raw_datasets.values())).features[data_args.audio_column_name].sampling_rate
|
| 433 |
+
if dataset_sampling_rate != feature_extractor.sampling_rate:
|
| 434 |
+
raw_datasets = raw_datasets.cast_column(
|
| 435 |
+
data_args.audio_column_name, datasets.features.Audio(sampling_rate=feature_extractor.sampling_rate)
|
| 436 |
+
)
|
| 437 |
+
|
| 438 |
+
# 7. Preprocessing the datasets.
|
| 439 |
+
# We need to read the audio files as arrays and tokenize the targets.
|
| 440 |
+
max_input_length = data_args.max_duration_in_seconds * feature_extractor.sampling_rate
|
| 441 |
+
min_input_length = data_args.min_duration_in_seconds * feature_extractor.sampling_rate
|
| 442 |
+
audio_column_name = data_args.audio_column_name
|
| 443 |
+
text_column_name = data_args.text_column_name
|
| 444 |
+
model_input_name = feature_extractor.model_input_names[0]
|
| 445 |
+
do_lower_case = data_args.do_lower_case
|
| 446 |
+
do_remove_punctuation = data_args.do_remove_punctuation
|
| 447 |
+
|
| 448 |
+
punctuation_to_remove = string.punctuation.replace("'", "") # don't remove apostrophes
|
| 449 |
+
punctuation_to_remove_regex = f"[{''.join(punctuation_to_remove)}]"
|
| 450 |
+
|
| 451 |
+
if data_args.max_train_samples is not None:
|
| 452 |
+
raw_datasets["train"] = raw_datasets["train"].take(data_args.max_train_samples)
|
| 453 |
+
|
| 454 |
+
if data_args.max_eval_samples is not None:
|
| 455 |
+
raw_datasets["eval"] = raw_datasets["eval"].take(data_args.max_eval_samples)
|
| 456 |
+
|
| 457 |
+
def prepare_dataset(batch):
|
| 458 |
+
# process audio
|
| 459 |
+
sample = batch[audio_column_name]
|
| 460 |
+
inputs = feature_extractor(sample["array"], sampling_rate=sample["sampling_rate"])
|
| 461 |
+
# process audio length
|
| 462 |
+
batch[model_input_name] = inputs.get(model_input_name)[0]
|
| 463 |
+
batch["input_length"] = len(sample["array"])
|
| 464 |
+
|
| 465 |
+
# process targets (only char no rome)
|
| 466 |
+
input_str = batch[text_column_name].lower().split('（')[0] if do_lower_case else batch[text_column_name].split('（')[0]
|
| 467 |
+
|
| 468 |
+
if do_remove_punctuation:
|
| 469 |
+
input_str = re.sub(punctuation_to_remove_regex, " ", input_str).strip()
|
| 470 |
+
input_str = re.sub("\s\s+", " ", input_str)
|
| 471 |
+
batch["labels"] = tokenizer(input_str).input_ids
|
| 472 |
+
return batch
|
| 473 |
+
|
| 474 |
+
with training_args.main_process_first(desc="dataset map pre-processing"):
|
| 475 |
+
vectorized_datasets = raw_datasets.map(
|
| 476 |
+
prepare_dataset,
|
| 477 |
+
remove_columns=raw_datasets_features,
|
| 478 |
+
).with_format("torch")
|
| 479 |
+
|
| 480 |
+
if training_args.do_train:
|
| 481 |
+
vectorized_datasets["train"] = vectorized_datasets["train"].shuffle(
|
| 482 |
+
buffer_size=data_args.shuffle_buffer_size,
|
| 483 |
+
seed=training_args.seed,
|
| 484 |
+
)
|
| 485 |
+
|
| 486 |
+
# filter training data that is shorter than min_input_length or longer than
|
| 487 |
+
# max_input_length
|
| 488 |
+
def is_audio_in_length_range(length):
|
| 489 |
+
return min_input_length < length < max_input_length
|
| 490 |
+
|
| 491 |
+
if training_args.do_train:
|
| 492 |
+
vectorized_datasets["train"] = vectorized_datasets["train"].filter(
|
| 493 |
+
is_audio_in_length_range,
|
| 494 |
+
input_columns=["input_length"],
|
| 495 |
+
)
|
| 496 |
+
|
| 497 |
+
# 8. Load Metric
|
| 498 |
+
cer_metric = evaluate.load("cer")
|
| 499 |
+
wer_metric = evaluate.load("wer")
|
| 500 |
+
do_normalize_eval = data_args.do_normalize_eval
|
| 501 |
+
|
| 502 |
+
def compute_metrics(pred):
|
| 503 |
+
pred_ids = pred.predictions
|
| 504 |
+
|
| 505 |
+
pred.label_ids[pred.label_ids == -100] = tokenizer.pad_token_id
|
| 506 |
+
|
| 507 |
+
pred_str = tokenizer.batch_decode(pred_ids, skip_special_tokens=True, normalize=do_normalize_eval)
|
| 508 |
+
# we do not want to group tokens when computing the metrics
|
| 509 |
+
label_str = tokenizer.batch_decode(pred.label_ids, skip_special_tokens=True, normalize=do_normalize_eval)
|
| 510 |
+
cer = 100 * cer_metric.compute(predictions=pred_str, references=label_str)
|
| 511 |
+
pred_str = [ryNormText.separ_char_word(x) for x in pred_str]
|
| 512 |
+
label_str = [ryNormText.separ_char_word(x) for x in label_str]
|
| 513 |
+
p = open('pred.txt','w')
|
| 514 |
+
p.write(f'{pred_str=}')
|
| 515 |
+
p.close()
|
| 516 |
+
p = open('label.txt','w')
|
| 517 |
+
p.write(f'{label_str=}')
|
| 518 |
+
p.close()
|
| 519 |
+
wer = 100 * wer_metric.compute(predictions=pred_str, references=label_str)
|
| 520 |
+
return {"wer": wer, "cer": cer}
|
| 521 |
+
|
| 522 |
+
# 9. Create a single speech processor
|
| 523 |
+
if is_main_process(training_args.local_rank):
|
| 524 |
+
# save feature extractor, tokenizer and config
|
| 525 |
+
feature_extractor.save_pretrained(training_args.output_dir)
|
| 526 |
+
tokenizer.save_pretrained(training_args.output_dir)
|
| 527 |
+
config.save_pretrained(training_args.output_dir)
|
| 528 |
+
|
| 529 |
+
processor = AutoProcessor.from_pretrained(training_args.output_dir)
|
| 530 |
+
|
| 531 |
+
# 10. Define data collator
|
| 532 |
+
data_collator = DataCollatorSpeechSeq2SeqWithPadding(
|
| 533 |
+
processor=processor,
|
| 534 |
+
decoder_start_token_id=model.config.decoder_start_token_id,
|
| 535 |
+
)
|
| 536 |
+
|
| 537 |
+
# 11. Configure Trainer
|
| 538 |
+
# Trainer callback to reinitialise and reshuffle the streamable datasets at the beginning of each epoch
|
| 539 |
+
class ShuffleCallback(TrainerCallback):
|
| 540 |
+
def on_epoch_begin(self, args, state, control, train_dataloader, **kwargs):
|
| 541 |
+
if isinstance(train_dataloader.dataset, IterableDatasetShard):
|
| 542 |
+
pass # set_epoch() is handled by the Trainer
|
| 543 |
+
elif isinstance(train_dataloader.dataset, IterableDataset):
|
| 544 |
+
train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)
|
| 545 |
+
|
| 546 |
+
# Initialize Trainer
|
| 547 |
+
trainer = Seq2SeqTrainer(
|
| 548 |
+
model=model,
|
| 549 |
+
args=training_args,
|
| 550 |
+
train_dataset=vectorized_datasets["train"] if training_args.do_train else None,
|
| 551 |
+
eval_dataset=vectorized_datasets["eval"] if training_args.do_eval else None,
|
| 552 |
+
tokenizer=feature_extractor,
|
| 553 |
+
data_collator=data_collator,
|
| 554 |
+
compute_metrics=compute_metrics if training_args.predict_with_generate else None,
|
| 555 |
+
callbacks=[ShuffleCallback()],
|
| 556 |
+
)
|
| 557 |
+
|
| 558 |
+
# 12. Training
|
| 559 |
+
if training_args.do_train:
|
| 560 |
+
checkpoint = None
|
| 561 |
+
if training_args.resume_from_checkpoint is not None:
|
| 562 |
+
checkpoint = training_args.resume_from_checkpoint
|
| 563 |
+
elif last_checkpoint is not None:
|
| 564 |
+
checkpoint = last_checkpoint
|
| 565 |
+
train_result = trainer.train(resume_from_checkpoint=checkpoint)
|
| 566 |
+
trainer.save_model() # Saves the feature extractor too for easy upload
|
| 567 |
+
|
| 568 |
+
metrics = train_result.metrics
|
| 569 |
+
if data_args.max_train_samples:
|
| 570 |
+
metrics["train_samples"] = data_args.max_train_samples
|
| 571 |
+
trainer.log_metrics("train", metrics)
|
| 572 |
+
trainer.save_metrics("train", metrics)
|
| 573 |
+
trainer.save_state()
|
| 574 |
+
|
| 575 |
+
# 13. Evaluation
|
| 576 |
+
results = {}
|
| 577 |
+
if training_args.do_eval:
|
| 578 |
+
logger.info("*** Evaluate ***")
|
| 579 |
+
metrics = trainer.evaluate(
|
| 580 |
+
|
| 581 |
+
metric_key_prefix="eval",
|
| 582 |
+
max_length=training_args.generation_max_length,
|
| 583 |
+
num_beams=training_args.generation_num_beams,
|
| 584 |
+
)
|
| 585 |
+
if data_args.max_eval_samples:
|
| 586 |
+
metrics["eval_samples"] = data_args.max_eval_samples
|
| 587 |
+
|
| 588 |
+
trainer.log_metrics("eval", metrics)
|
| 589 |
+
trainer.save_metrics("eval", metrics)
|
| 590 |
+
|
| 591 |
+
# 14. Write Training Stats
|
| 592 |
+
kwargs = {
|
| 593 |
+
"finetuned_from": model_args.model_name_or_path,
|
| 594 |
+
"tasks": "automatic-speech-recognition",
|
| 595 |
+
"tags": "whisper-event",
|
| 596 |
+
}
|
| 597 |
+
if data_args.dataset_name is not None:
|
| 598 |
+
kwargs["dataset_tags"] = data_args.dataset_name
|
| 599 |
+
if data_args.dataset_config_name is not None:
|
| 600 |
+
kwargs["dataset"] = f"{data_args.dataset_name} {data_args.dataset_config_name}"
|
| 601 |
+
else:
|
| 602 |
+
kwargs["dataset"] = data_args.dataset_name
|
| 603 |
+
if "common_voice" in data_args.dataset_name:
|
| 604 |
+
kwargs["language"] = data_args.dataset_config_name
|
| 605 |
+
if model_args.model_index_name is not None:
|
| 606 |
+
kwargs["model_name"] = model_args.model_index_name
|
| 607 |
+
|
| 608 |
+
if training_args.push_to_hub:
|
| 609 |
+
trainer.push_to_hub(**kwargs)
|
| 610 |
+
else:
|
| 611 |
+
trainer.create_model_card(**kwargs)
|
| 612 |
+
|
| 613 |
+
return results
|
| 614 |
+
|
| 615 |
+
|
| 616 |
+
if __name__ == "__main__":
|
| 617 |
+
main()
|
ryNormText.py
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import string, re, opencc
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
全型2半型= str.maketrans(
|
| 5 |
+
' ０１２３４５６７８９'
|
| 6 |
+
'ａｂｃｄｅｆｇｈｉｊｋｌｍｎｏｐｑｒｓｔｕｖｗｘｙｚ'
|
| 7 |
+
'ＡＢＣＤＥＦＧＨＩＪＫＬＭＮＯＰＱＲＳＴＵＶＷＸＹＺ'
|
| 8 |
+
'！゛＃＄％＆（）＊＋、ー。／：；〈＝〉？＠［］＾＿‘｛｜｝～',
|
| 9 |
+
' 0123456789'
|
| 10 |
+
'abcdefghijklmnopqrstuvwxyz'
|
| 11 |
+
'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
|
| 12 |
+
'!"#$%&()*+,-./:;<=>?@[]^_`{|}~'
|
| 13 |
+
)
|
| 14 |
+
|
| 15 |
+
def 把怪字修進unicode(xStr):
|
| 16 |
+
xStr= re.sub('\uf5c3','𪜶', xStr)
|
| 17 |
+
return xStr
|
| 18 |
+
|
| 19 |
+
def ryNormText(s):
|
| 20 |
+
"""
|
| 21 |
+
<<<None>>> ==> 刪除
|
| 22 |
+
標點 ==> 空白
|
| 23 |
+
連續空白 ==> 1個空白
|
| 24 |
+
簡繁
|
| 25 |
+
"""
|
| 26 |
+
|
| 27 |
+
punc1= string.punctuation # 這是為英文
|
| 28 |
+
punc1
|
| 29 |
+
punc2= '。，﹐、！？：：；『』「」…,\n' # 這是為中文，尚未完備！！
|
| 30 |
+
|
| 31 |
+
punc= f"[{punc1}{punc2}]" ## 這是 regular expression 的 pattern
|
| 32 |
+
|
| 33 |
+
## <<<None>>> ==> 刪除
|
| 34 |
+
s= re.sub('<<<None>>>','',s)
|
| 35 |
+
|
| 36 |
+
# 標點 ==> 空白
|
| 37 |
+
s= re.sub(punc,' ',s)
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
# 連續空白 ==> 1個空白
|
| 41 |
+
s= re.sub('[ ]+',' ',s)
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
# 空白 ==> 刪除
|
| 45 |
+
s= re.sub(' ','',s)
|
| 46 |
+
|
| 47 |
+
s= 把怪字修進unicode(s)
|
| 48 |
+
|
| 49 |
+
# 簡繁
|
| 50 |
+
s= opencc.OpenCC('s2tw').convert(s)
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
return s
|
| 54 |
+
|
| 55 |
+
import unicodedata
|
| 56 |
+
import re
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def separ_char_word(inputString= '我是呂仁園 Renyuan Lyu'):
|
| 60 |
+
|
| 61 |
+
inputString= 把怪字修進unicode(inputString)
|
| 62 |
+
|
| 63 |
+
y= ''
|
| 64 |
+
for x in inputString:
|
| 65 |
+
y += x
|
| 66 |
+
try:
|
| 67 |
+
un= unicodedata.name(x)
|
| 68 |
+
if un.startswith('CJK'):
|
| 69 |
+
y += ' '
|
| 70 |
+
else:
|
| 71 |
+
pass
|
| 72 |
+
except Exception as ex:
|
| 73 |
+
y = ' '+y+' '
|
| 74 |
+
print(f'ryErr:(def 中英分開:){ex= }\t【{x= }】\t{inputString= }')
|
| 75 |
+
|
| 76 |
+
y= re.sub('[ ]+',' ', y) #連續空白只保留1個空白
|
| 77 |
+
return y
|
| 78 |
+
|
| 79 |
+
#q= 中英分開('大家好 da jia hao 我是呂仁園 I am Renyuan Lyu')
|
| 80 |
+
|
| 81 |
+
#print(q)
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|startoftranscript|>",
|
| 5 |
+
"<|en|>",
|
| 6 |
+
"<|zh|>",
|
| 7 |
+
"<|de|>",
|
| 8 |
+
"<|es|>",
|
| 9 |
+
"<|ru|>",
|
| 10 |
+
"<|ko|>",
|
| 11 |
+
"<|fr|>",
|
| 12 |
+
"<|ja|>",
|
| 13 |
+
"<|pt|>",
|
| 14 |
+
"<|tr|>",
|
| 15 |
+
"<|pl|>",
|
| 16 |
+
"<|ca|>",
|
| 17 |
+
"<|nl|>",
|
| 18 |
+
"<|ar|>",
|
| 19 |
+
"<|sv|>",
|
| 20 |
+
"<|it|>",
|
| 21 |
+
"<|id|>",
|
| 22 |
+
"<|hi|>",
|
| 23 |
+
"<|fi|>",
|
| 24 |
+
"<|vi|>",
|
| 25 |
+
"<|he|>",
|
| 26 |
+
"<|uk|>",
|
| 27 |
+
"<|el|>",
|
| 28 |
+
"<|ms|>",
|
| 29 |
+
"<|cs|>",
|
| 30 |
+
"<|ro|>",
|
| 31 |
+
"<|da|>",
|
| 32 |
+
"<|hu|>",
|
| 33 |
+
"<|ta|>",
|
| 34 |
+
"<|no|>",
|
| 35 |
+
"<|th|>",
|
| 36 |
+
"<|ur|>",
|
| 37 |
+
"<|hr|>",
|
| 38 |
+
"<|bg|>",
|
| 39 |
+
"<|lt|>",
|
| 40 |
+
"<|la|>",
|
| 41 |
+
"<|mi|>",
|
| 42 |
+
"<|ml|>",
|
| 43 |
+
"<|cy|>",
|
| 44 |
+
"<|sk|>",
|
| 45 |
+
"<|te|>",
|
| 46 |
+
"<|fa|>",
|
| 47 |
+
"<|lv|>",
|
| 48 |
+
"<|bn|>",
|
| 49 |
+
"<|sr|>",
|
| 50 |
+
"<|az|>",
|
| 51 |
+
"<|sl|>",
|
| 52 |
+
"<|kn|>",
|
| 53 |
+
"<|et|>",
|
| 54 |
+
"<|mk|>",
|
| 55 |
+
"<|br|>",
|
| 56 |
+
"<|eu|>",
|
| 57 |
+
"<|is|>",
|
| 58 |
+
"<|hy|>",
|
| 59 |
+
"<|ne|>",
|
| 60 |
+
"<|mn|>",
|
| 61 |
+
"<|bs|>",
|
| 62 |
+
"<|kk|>",
|
| 63 |
+
"<|sq|>",
|
| 64 |
+
"<|sw|>",
|
| 65 |
+
"<|gl|>",
|
| 66 |
+
"<|mr|>",
|
| 67 |
+
"<|pa|>",
|
| 68 |
+
"<|si|>",
|
| 69 |
+
"<|km|>",
|
| 70 |
+
"<|sn|>",
|
| 71 |
+
"<|yo|>",
|
| 72 |
+
"<|so|>",
|
| 73 |
+
"<|af|>",
|
| 74 |
+
"<|oc|>",
|
| 75 |
+
"<|ka|>",
|
| 76 |
+
"<|be|>",
|
| 77 |
+
"<|tg|>",
|
| 78 |
+
"<|sd|>",
|
| 79 |
+
"<|gu|>",
|
| 80 |
+
"<|am|>",
|
| 81 |
+
"<|yi|>",
|
| 82 |
+
"<|lo|>",
|
| 83 |
+
"<|uz|>",
|
| 84 |
+
"<|fo|>",
|
| 85 |
+
"<|ht|>",
|
| 86 |
+
"<|ps|>",
|
| 87 |
+
"<|tk|>",
|
| 88 |
+
"<|nn|>",
|
| 89 |
+
"<|mt|>",
|
| 90 |
+
"<|sa|>",
|
| 91 |
+
"<|lb|>",
|
| 92 |
+
"<|my|>",
|
| 93 |
+
"<|bo|>",
|
| 94 |
+
"<|tl|>",
|
| 95 |
+
"<|mg|>",
|
| 96 |
+
"<|as|>",
|
| 97 |
+
"<|tt|>",
|
| 98 |
+
"<|haw|>",
|
| 99 |
+
"<|ln|>",
|
| 100 |
+
"<|ha|>",
|
| 101 |
+
"<|ba|>",
|
| 102 |
+
"<|jw|>",
|
| 103 |
+
"<|su|>",
|
| 104 |
+
"<|translate|>",
|
| 105 |
+
"<|transcribe|>",
|
| 106 |
+
"<|startoflm|>",
|
| 107 |
+
"<|startofprev|>",
|
| 108 |
+
"<|nocaptions|>",
|
| 109 |
+
"<|notimestamps|>"
|
| 110 |
+
],
|
| 111 |
+
"bos_token": {
|
| 112 |
+
"content": "<|endoftext|>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": true,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"eos_token": {
|
| 119 |
+
"content": "<|endoftext|>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
},
|
| 125 |
+
"pad_token": "<|endoftext|>",
|
| 126 |
+
"unk_token": {
|
| 127 |
+
"content": "<|endoftext|>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false
|
| 132 |
+
}
|
| 133 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"eos_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"errors": "replace",
|
| 21 |
+
"model_max_length": 1024,
|
| 22 |
+
"name_or_path": "openai/whisper-large-v2",
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"processor_class": "WhisperProcessor",
|
| 25 |
+
"return_attention_mask": false,
|
| 26 |
+
"special_tokens_map_file": null,
|
| 27 |
+
"tokenizer_class": "WhisperTokenizer",
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<|endoftext|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.05,
|
| 3 |
+
"train_loss": 3.0522214595794677,
|
| 4 |
+
"train_runtime": 5458.8622,
|
| 5 |
+
"train_samples_per_second": 1.832,
|
| 6 |
+
"train_steps_per_second": 0.916
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1275 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.0532,
|
| 5 |
+
"global_step": 5000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 4.2000000000000006e-07,
|
| 13 |
+
"loss": 2.3259,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 9.000000000000001e-07,
|
| 19 |
+
"loss": 1.7615,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"learning_rate": 1.3800000000000001e-06,
|
| 25 |
+
"loss": 1.2375,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.02,
|
| 30 |
+
"learning_rate": 1.8800000000000002e-06,
|
| 31 |
+
"loss": 1.3112,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.03,
|
| 36 |
+
"learning_rate": 2.38e-06,
|
| 37 |
+
"loss": 1.3986,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03,
|
| 42 |
+
"learning_rate": 2.88e-06,
|
| 43 |
+
"loss": 1.6643,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04,
|
| 48 |
+
"learning_rate": 3.3800000000000007e-06,
|
| 49 |
+
"loss": 1.7064,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.04,
|
| 54 |
+
"learning_rate": 3.88e-06,
|
| 55 |
+
"loss": 1.7026,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.04,
|
| 60 |
+
"learning_rate": 4.38e-06,
|
| 61 |
+
"loss": 2.0459,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.05,
|
| 66 |
+
"learning_rate": 4.880000000000001e-06,
|
| 67 |
+
"loss": 2.3189,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.06,
|
| 72 |
+
"learning_rate": 5.380000000000001e-06,
|
| 73 |
+
"loss": 2.647,
|
| 74 |
+
"step": 275
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.06,
|
| 78 |
+
"learning_rate": 5.8800000000000005e-06,
|
| 79 |
+
"loss": 2.4019,
|
| 80 |
+
"step": 300
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.07,
|
| 84 |
+
"learning_rate": 6.380000000000001e-06,
|
| 85 |
+
"loss": 2.9076,
|
| 86 |
+
"step": 325
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.07,
|
| 90 |
+
"learning_rate": 6.860000000000001e-06,
|
| 91 |
+
"loss": 4.1248,
|
| 92 |
+
"step": 350
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.07,
|
| 96 |
+
"learning_rate": 7.360000000000001e-06,
|
| 97 |
+
"loss": 2.9751,
|
| 98 |
+
"step": 375
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.08,
|
| 102 |
+
"learning_rate": 7.860000000000001e-06,
|
| 103 |
+
"loss": 3.1863,
|
| 104 |
+
"step": 400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.09,
|
| 108 |
+
"learning_rate": 8.36e-06,
|
| 109 |
+
"loss": 3.1017,
|
| 110 |
+
"step": 425
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.09,
|
| 114 |
+
"learning_rate": 8.860000000000002e-06,
|
| 115 |
+
"loss": 3.3757,
|
| 116 |
+
"step": 450
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.1,
|
| 120 |
+
"learning_rate": 9.360000000000002e-06,
|
| 121 |
+
"loss": 4.871,
|
| 122 |
+
"step": 475
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.1,
|
| 126 |
+
"learning_rate": 9.86e-06,
|
| 127 |
+
"loss": 7.6053,
|
| 128 |
+
"step": 500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1,
|
| 132 |
+
"learning_rate": 9.960000000000001e-06,
|
| 133 |
+
"loss": 4.4155,
|
| 134 |
+
"step": 525
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.11,
|
| 138 |
+
"learning_rate": 9.904444444444445e-06,
|
| 139 |
+
"loss": 4.5183,
|
| 140 |
+
"step": 550
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.12,
|
| 144 |
+
"learning_rate": 9.84888888888889e-06,
|
| 145 |
+
"loss": 4.1442,
|
| 146 |
+
"step": 575
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.12,
|
| 150 |
+
"learning_rate": 9.793333333333333e-06,
|
| 151 |
+
"loss": 4.1241,
|
| 152 |
+
"step": 600
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.12,
|
| 156 |
+
"learning_rate": 9.737777777777779e-06,
|
| 157 |
+
"loss": 3.9046,
|
| 158 |
+
"step": 625
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.13,
|
| 162 |
+
"learning_rate": 9.682222222222223e-06,
|
| 163 |
+
"loss": 3.8142,
|
| 164 |
+
"step": 650
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.14,
|
| 168 |
+
"learning_rate": 9.626666666666667e-06,
|
| 169 |
+
"loss": 3.6618,
|
| 170 |
+
"step": 675
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.14,
|
| 174 |
+
"learning_rate": 9.571111111111113e-06,
|
| 175 |
+
"loss": 3.6848,
|
| 176 |
+
"step": 700
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.14,
|
| 180 |
+
"learning_rate": 9.515555555555557e-06,
|
| 181 |
+
"loss": 3.6017,
|
| 182 |
+
"step": 725
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.15,
|
| 186 |
+
"learning_rate": 9.460000000000001e-06,
|
| 187 |
+
"loss": 3.5401,
|
| 188 |
+
"step": 750
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.15,
|
| 192 |
+
"learning_rate": 9.404444444444445e-06,
|
| 193 |
+
"loss": 3.7507,
|
| 194 |
+
"step": 775
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.0,
|
| 198 |
+
"learning_rate": 9.348888888888889e-06,
|
| 199 |
+
"loss": 3.3527,
|
| 200 |
+
"step": 800
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.01,
|
| 204 |
+
"learning_rate": 9.293333333333335e-06,
|
| 205 |
+
"loss": 3.4445,
|
| 206 |
+
"step": 825
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.01,
|
| 210 |
+
"learning_rate": 9.237777777777779e-06,
|
| 211 |
+
"loss": 3.3492,
|
| 212 |
+
"step": 850
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.02,
|
| 216 |
+
"learning_rate": 9.182222222222223e-06,
|
| 217 |
+
"loss": 3.4195,
|
| 218 |
+
"step": 875
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.02,
|
| 222 |
+
"learning_rate": 9.126666666666667e-06,
|
| 223 |
+
"loss": 3.6324,
|
| 224 |
+
"step": 900
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.03,
|
| 228 |
+
"learning_rate": 9.07111111111111e-06,
|
| 229 |
+
"loss": 3.5551,
|
| 230 |
+
"step": 925
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.03,
|
| 234 |
+
"learning_rate": 9.015555555555557e-06,
|
| 235 |
+
"loss": 3.6139,
|
| 236 |
+
"step": 950
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.04,
|
| 240 |
+
"learning_rate": 8.96e-06,
|
| 241 |
+
"loss": 3.3878,
|
| 242 |
+
"step": 975
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.04,
|
| 246 |
+
"learning_rate": 8.904444444444446e-06,
|
| 247 |
+
"loss": 3.5696,
|
| 248 |
+
"step": 1000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.04,
|
| 252 |
+
"eval_cer": 96.89103531542409,
|
| 253 |
+
"eval_loss": 3.418963670730591,
|
| 254 |
+
"eval_runtime": 273.6647,
|
| 255 |
+
"eval_samples_per_second": 3.603,
|
| 256 |
+
"eval_steps_per_second": 1.801,
|
| 257 |
+
"eval_wer": 96.85496183206106,
|
| 258 |
+
"step": 1000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.05,
|
| 262 |
+
"learning_rate": 8.848888888888889e-06,
|
| 263 |
+
"loss": 3.6154,
|
| 264 |
+
"step": 1025
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.05,
|
| 268 |
+
"learning_rate": 8.793333333333334e-06,
|
| 269 |
+
"loss": 3.4399,
|
| 270 |
+
"step": 1050
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.06,
|
| 274 |
+
"learning_rate": 8.737777777777778e-06,
|
| 275 |
+
"loss": 3.3262,
|
| 276 |
+
"step": 1075
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.06,
|
| 280 |
+
"learning_rate": 8.682222222222222e-06,
|
| 281 |
+
"loss": 3.4615,
|
| 282 |
+
"step": 1100
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.07,
|
| 286 |
+
"learning_rate": 8.626666666666668e-06,
|
| 287 |
+
"loss": 3.2971,
|
| 288 |
+
"step": 1125
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.07,
|
| 292 |
+
"learning_rate": 8.571111111111112e-06,
|
| 293 |
+
"loss": 3.4235,
|
| 294 |
+
"step": 1150
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.08,
|
| 298 |
+
"learning_rate": 8.515555555555556e-06,
|
| 299 |
+
"loss": 3.252,
|
| 300 |
+
"step": 1175
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.08,
|
| 304 |
+
"learning_rate": 8.46e-06,
|
| 305 |
+
"loss": 3.3725,
|
| 306 |
+
"step": 1200
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.09,
|
| 310 |
+
"learning_rate": 8.404444444444444e-06,
|
| 311 |
+
"loss": 3.4539,
|
| 312 |
+
"step": 1225
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.09,
|
| 316 |
+
"learning_rate": 8.34888888888889e-06,
|
| 317 |
+
"loss": 3.3736,
|
| 318 |
+
"step": 1250
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1,
|
| 322 |
+
"learning_rate": 8.293333333333334e-06,
|
| 323 |
+
"loss": 3.3606,
|
| 324 |
+
"step": 1275
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.1,
|
| 328 |
+
"learning_rate": 8.237777777777778e-06,
|
| 329 |
+
"loss": 3.4193,
|
| 330 |
+
"step": 1300
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.11,
|
| 334 |
+
"learning_rate": 8.182222222222222e-06,
|
| 335 |
+
"loss": 3.3679,
|
| 336 |
+
"step": 1325
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.11,
|
| 340 |
+
"learning_rate": 8.126666666666668e-06,
|
| 341 |
+
"loss": 3.5329,
|
| 342 |
+
"step": 1350
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.12,
|
| 346 |
+
"learning_rate": 8.071111111111112e-06,
|
| 347 |
+
"loss": 3.3347,
|
| 348 |
+
"step": 1375
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.12,
|
| 352 |
+
"learning_rate": 8.015555555555556e-06,
|
| 353 |
+
"loss": 3.3093,
|
| 354 |
+
"step": 1400
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.13,
|
| 358 |
+
"learning_rate": 7.960000000000002e-06,
|
| 359 |
+
"loss": 3.3035,
|
| 360 |
+
"step": 1425
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.13,
|
| 364 |
+
"learning_rate": 7.904444444444444e-06,
|
| 365 |
+
"loss": 3.4493,
|
| 366 |
+
"step": 1450
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.14,
|
| 370 |
+
"learning_rate": 7.84888888888889e-06,
|
| 371 |
+
"loss": 3.2347,
|
| 372 |
+
"step": 1475
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.14,
|
| 376 |
+
"learning_rate": 7.793333333333334e-06,
|
| 377 |
+
"loss": 3.2076,
|
| 378 |
+
"step": 1500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.15,
|
| 382 |
+
"learning_rate": 7.737777777777778e-06,
|
| 383 |
+
"loss": 3.2862,
|
| 384 |
+
"step": 1525
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.15,
|
| 388 |
+
"learning_rate": 7.682222222222224e-06,
|
| 389 |
+
"loss": 3.4486,
|
| 390 |
+
"step": 1550
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.16,
|
| 394 |
+
"learning_rate": 7.626666666666668e-06,
|
| 395 |
+
"loss": 3.3531,
|
| 396 |
+
"step": 1575
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.0,
|
| 400 |
+
"learning_rate": 7.571111111111112e-06,
|
| 401 |
+
"loss": 3.435,
|
| 402 |
+
"step": 1600
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.01,
|
| 406 |
+
"learning_rate": 7.515555555555556e-06,
|
| 407 |
+
"loss": 3.3428,
|
| 408 |
+
"step": 1625
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.01,
|
| 412 |
+
"learning_rate": 7.4600000000000006e-06,
|
| 413 |
+
"loss": 3.2712,
|
| 414 |
+
"step": 1650
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.02,
|
| 418 |
+
"learning_rate": 7.4044444444444455e-06,
|
| 419 |
+
"loss": 3.147,
|
| 420 |
+
"step": 1675
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.02,
|
| 424 |
+
"learning_rate": 7.3488888888888895e-06,
|
| 425 |
+
"loss": 3.2841,
|
| 426 |
+
"step": 1700
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.03,
|
| 430 |
+
"learning_rate": 7.2933333333333335e-06,
|
| 431 |
+
"loss": 3.1548,
|
| 432 |
+
"step": 1725
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.03,
|
| 436 |
+
"learning_rate": 7.237777777777778e-06,
|
| 437 |
+
"loss": 3.0778,
|
| 438 |
+
"step": 1750
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.04,
|
| 442 |
+
"learning_rate": 7.1822222222222224e-06,
|
| 443 |
+
"loss": 3.1293,
|
| 444 |
+
"step": 1775
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.04,
|
| 448 |
+
"learning_rate": 7.126666666666667e-06,
|
| 449 |
+
"loss": 3.3325,
|
| 450 |
+
"step": 1800
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.05,
|
| 454 |
+
"learning_rate": 7.071111111111112e-06,
|
| 455 |
+
"loss": 3.1438,
|
| 456 |
+
"step": 1825
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.05,
|
| 460 |
+
"learning_rate": 7.015555555555556e-06,
|
| 461 |
+
"loss": 3.3838,
|
| 462 |
+
"step": 1850
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.06,
|
| 466 |
+
"learning_rate": 6.96e-06,
|
| 467 |
+
"loss": 3.344,
|
| 468 |
+
"step": 1875
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.06,
|
| 472 |
+
"learning_rate": 6.904444444444444e-06,
|
| 473 |
+
"loss": 3.1949,
|
| 474 |
+
"step": 1900
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.07,
|
| 478 |
+
"learning_rate": 6.848888888888889e-06,
|
| 479 |
+
"loss": 3.2732,
|
| 480 |
+
"step": 1925
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.07,
|
| 484 |
+
"learning_rate": 6.793333333333334e-06,
|
| 485 |
+
"loss": 3.2508,
|
| 486 |
+
"step": 1950
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.08,
|
| 490 |
+
"learning_rate": 6.737777777777779e-06,
|
| 491 |
+
"loss": 3.1962,
|
| 492 |
+
"step": 1975
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.08,
|
| 496 |
+
"learning_rate": 6.682222222222223e-06,
|
| 497 |
+
"loss": 3.1453,
|
| 498 |
+
"step": 2000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.08,
|
| 502 |
+
"eval_cer": 98.94355568970722,
|
| 503 |
+
"eval_loss": 3.238253116607666,
|
| 504 |
+
"eval_runtime": 276.3056,
|
| 505 |
+
"eval_samples_per_second": 3.569,
|
| 506 |
+
"eval_steps_per_second": 1.784,
|
| 507 |
+
"eval_wer": 98.93129770992365,
|
| 508 |
+
"step": 2000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.09,
|
| 512 |
+
"learning_rate": 6.626666666666667e-06,
|
| 513 |
+
"loss": 3.2259,
|
| 514 |
+
"step": 2025
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.09,
|
| 518 |
+
"learning_rate": 6.571111111111111e-06,
|
| 519 |
+
"loss": 3.2412,
|
| 520 |
+
"step": 2050
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.1,
|
| 524 |
+
"learning_rate": 6.515555555555556e-06,
|
| 525 |
+
"loss": 3.1211,
|
| 526 |
+
"step": 2075
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.1,
|
| 530 |
+
"learning_rate": 6.460000000000001e-06,
|
| 531 |
+
"loss": 2.9139,
|
| 532 |
+
"step": 2100
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.11,
|
| 536 |
+
"learning_rate": 6.404444444444446e-06,
|
| 537 |
+
"loss": 3.1701,
|
| 538 |
+
"step": 2125
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.11,
|
| 542 |
+
"learning_rate": 6.348888888888889e-06,
|
| 543 |
+
"loss": 3.1944,
|
| 544 |
+
"step": 2150
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.12,
|
| 548 |
+
"learning_rate": 6.293333333333334e-06,
|
| 549 |
+
"loss": 3.1589,
|
| 550 |
+
"step": 2175
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.12,
|
| 554 |
+
"learning_rate": 6.237777777777778e-06,
|
| 555 |
+
"loss": 3.2229,
|
| 556 |
+
"step": 2200
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.13,
|
| 560 |
+
"learning_rate": 6.182222222222223e-06,
|
| 561 |
+
"loss": 3.2401,
|
| 562 |
+
"step": 2225
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.13,
|
| 566 |
+
"learning_rate": 6.126666666666668e-06,
|
| 567 |
+
"loss": 3.2551,
|
| 568 |
+
"step": 2250
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.14,
|
| 572 |
+
"learning_rate": 6.0711111111111125e-06,
|
| 573 |
+
"loss": 2.9634,
|
| 574 |
+
"step": 2275
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.14,
|
| 578 |
+
"learning_rate": 6.015555555555556e-06,
|
| 579 |
+
"loss": 3.0801,
|
| 580 |
+
"step": 2300
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 2.15,
|
| 584 |
+
"learning_rate": 5.9600000000000005e-06,
|
| 585 |
+
"loss": 3.1698,
|
| 586 |
+
"step": 2325
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.15,
|
| 590 |
+
"learning_rate": 5.9044444444444446e-06,
|
| 591 |
+
"loss": 3.1864,
|
| 592 |
+
"step": 2350
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 3.0,
|
| 596 |
+
"learning_rate": 5.8488888888888895e-06,
|
| 597 |
+
"loss": 3.1402,
|
| 598 |
+
"step": 2375
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 3.01,
|
| 602 |
+
"learning_rate": 5.793333333333334e-06,
|
| 603 |
+
"loss": 3.1443,
|
| 604 |
+
"step": 2400
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.01,
|
| 608 |
+
"learning_rate": 5.737777777777778e-06,
|
| 609 |
+
"loss": 2.9661,
|
| 610 |
+
"step": 2425
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 3.02,
|
| 614 |
+
"learning_rate": 5.682222222222222e-06,
|
| 615 |
+
"loss": 3.0652,
|
| 616 |
+
"step": 2450
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 3.02,
|
| 620 |
+
"learning_rate": 5.626666666666667e-06,
|
| 621 |
+
"loss": 3.0405,
|
| 622 |
+
"step": 2475
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 3.03,
|
| 626 |
+
"learning_rate": 5.571111111111111e-06,
|
| 627 |
+
"loss": 2.9499,
|
| 628 |
+
"step": 2500
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 3.03,
|
| 632 |
+
"learning_rate": 5.515555555555556e-06,
|
| 633 |
+
"loss": 3.1246,
|
| 634 |
+
"step": 2525
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 3.04,
|
| 638 |
+
"learning_rate": 5.460000000000001e-06,
|
| 639 |
+
"loss": 3.0122,
|
| 640 |
+
"step": 2550
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.04,
|
| 644 |
+
"learning_rate": 5.404444444444444e-06,
|
| 645 |
+
"loss": 3.0258,
|
| 646 |
+
"step": 2575
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.05,
|
| 650 |
+
"learning_rate": 5.348888888888889e-06,
|
| 651 |
+
"loss": 3.1414,
|
| 652 |
+
"step": 2600
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 3.05,
|
| 656 |
+
"learning_rate": 5.293333333333334e-06,
|
| 657 |
+
"loss": 3.1096,
|
| 658 |
+
"step": 2625
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 3.06,
|
| 662 |
+
"learning_rate": 5.237777777777778e-06,
|
| 663 |
+
"loss": 3.0937,
|
| 664 |
+
"step": 2650
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 3.06,
|
| 668 |
+
"learning_rate": 5.182222222222223e-06,
|
| 669 |
+
"loss": 3.0308,
|
| 670 |
+
"step": 2675
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 3.07,
|
| 674 |
+
"learning_rate": 5.126666666666668e-06,
|
| 675 |
+
"loss": 3.1702,
|
| 676 |
+
"step": 2700
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 3.07,
|
| 680 |
+
"learning_rate": 5.071111111111111e-06,
|
| 681 |
+
"loss": 3.1638,
|
| 682 |
+
"step": 2725
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 3.08,
|
| 686 |
+
"learning_rate": 5.015555555555556e-06,
|
| 687 |
+
"loss": 2.9025,
|
| 688 |
+
"step": 2750
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.08,
|
| 692 |
+
"learning_rate": 4.960000000000001e-06,
|
| 693 |
+
"loss": 3.0278,
|
| 694 |
+
"step": 2775
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 3.09,
|
| 698 |
+
"learning_rate": 4.904444444444445e-06,
|
| 699 |
+
"loss": 3.0397,
|
| 700 |
+
"step": 2800
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 3.09,
|
| 704 |
+
"learning_rate": 4.848888888888889e-06,
|
| 705 |
+
"loss": 3.0413,
|
| 706 |
+
"step": 2825
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 3.1,
|
| 710 |
+
"learning_rate": 4.793333333333334e-06,
|
| 711 |
+
"loss": 3.1721,
|
| 712 |
+
"step": 2850
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 3.1,
|
| 716 |
+
"learning_rate": 4.737777777777779e-06,
|
| 717 |
+
"loss": 2.9547,
|
| 718 |
+
"step": 2875
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 3.11,
|
| 722 |
+
"learning_rate": 4.682222222222223e-06,
|
| 723 |
+
"loss": 2.974,
|
| 724 |
+
"step": 2900
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 3.11,
|
| 728 |
+
"learning_rate": 4.626666666666667e-06,
|
| 729 |
+
"loss": 3.0297,
|
| 730 |
+
"step": 2925
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 3.12,
|
| 734 |
+
"learning_rate": 4.571111111111112e-06,
|
| 735 |
+
"loss": 2.9829,
|
| 736 |
+
"step": 2950
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 3.12,
|
| 740 |
+
"learning_rate": 4.515555555555556e-06,
|
| 741 |
+
"loss": 2.8869,
|
| 742 |
+
"step": 2975
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 3.13,
|
| 746 |
+
"learning_rate": 4.4600000000000005e-06,
|
| 747 |
+
"loss": 3.0722,
|
| 748 |
+
"step": 3000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 3.13,
|
| 752 |
+
"eval_cer": 158.52701479022033,
|
| 753 |
+
"eval_loss": 3.20432710647583,
|
| 754 |
+
"eval_runtime": 318.685,
|
| 755 |
+
"eval_samples_per_second": 3.094,
|
| 756 |
+
"eval_steps_per_second": 1.547,
|
| 757 |
+
"eval_wer": 129.06870229007635,
|
| 758 |
+
"step": 3000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.13,
|
| 762 |
+
"learning_rate": 4.404444444444445e-06,
|
| 763 |
+
"loss": 2.9035,
|
| 764 |
+
"step": 3025
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 3.14,
|
| 768 |
+
"learning_rate": 4.348888888888889e-06,
|
| 769 |
+
"loss": 2.9127,
|
| 770 |
+
"step": 3050
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 3.14,
|
| 774 |
+
"learning_rate": 4.2933333333333334e-06,
|
| 775 |
+
"loss": 3.1372,
|
| 776 |
+
"step": 3075
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 3.15,
|
| 780 |
+
"learning_rate": 4.2377777777777775e-06,
|
| 781 |
+
"loss": 2.9721,
|
| 782 |
+
"step": 3100
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 3.15,
|
| 786 |
+
"learning_rate": 4.182222222222222e-06,
|
| 787 |
+
"loss": 2.9846,
|
| 788 |
+
"step": 3125
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.16,
|
| 792 |
+
"learning_rate": 4.126666666666667e-06,
|
| 793 |
+
"loss": 3.0426,
|
| 794 |
+
"step": 3150
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 4.0,
|
| 798 |
+
"learning_rate": 4.071111111111111e-06,
|
| 799 |
+
"loss": 2.9058,
|
| 800 |
+
"step": 3175
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 4.01,
|
| 804 |
+
"learning_rate": 4.015555555555556e-06,
|
| 805 |
+
"loss": 2.8259,
|
| 806 |
+
"step": 3200
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 4.01,
|
| 810 |
+
"learning_rate": 3.96e-06,
|
| 811 |
+
"loss": 2.9893,
|
| 812 |
+
"step": 3225
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 4.02,
|
| 816 |
+
"learning_rate": 3.904444444444444e-06,
|
| 817 |
+
"loss": 2.9297,
|
| 818 |
+
"step": 3250
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 4.02,
|
| 822 |
+
"learning_rate": 3.848888888888889e-06,
|
| 823 |
+
"loss": 2.8989,
|
| 824 |
+
"step": 3275
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 4.03,
|
| 828 |
+
"learning_rate": 3.793333333333334e-06,
|
| 829 |
+
"loss": 2.9417,
|
| 830 |
+
"step": 3300
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 4.03,
|
| 834 |
+
"learning_rate": 3.737777777777778e-06,
|
| 835 |
+
"loss": 2.9383,
|
| 836 |
+
"step": 3325
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 4.04,
|
| 840 |
+
"learning_rate": 3.6822222222222225e-06,
|
| 841 |
+
"loss": 2.8867,
|
| 842 |
+
"step": 3350
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 4.04,
|
| 846 |
+
"learning_rate": 3.6266666666666674e-06,
|
| 847 |
+
"loss": 2.9945,
|
| 848 |
+
"step": 3375
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 4.05,
|
| 852 |
+
"learning_rate": 3.5711111111111114e-06,
|
| 853 |
+
"loss": 2.9077,
|
| 854 |
+
"step": 3400
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 4.05,
|
| 858 |
+
"learning_rate": 3.515555555555556e-06,
|
| 859 |
+
"loss": 2.8711,
|
| 860 |
+
"step": 3425
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 4.06,
|
| 864 |
+
"learning_rate": 3.46e-06,
|
| 865 |
+
"loss": 2.9767,
|
| 866 |
+
"step": 3450
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 4.06,
|
| 870 |
+
"learning_rate": 3.404444444444445e-06,
|
| 871 |
+
"loss": 2.8937,
|
| 872 |
+
"step": 3475
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 4.07,
|
| 876 |
+
"learning_rate": 3.3488888888888892e-06,
|
| 877 |
+
"loss": 2.9073,
|
| 878 |
+
"step": 3500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 4.07,
|
| 882 |
+
"learning_rate": 3.2933333333333333e-06,
|
| 883 |
+
"loss": 2.7517,
|
| 884 |
+
"step": 3525
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 4.08,
|
| 888 |
+
"learning_rate": 3.237777777777778e-06,
|
| 889 |
+
"loss": 3.0988,
|
| 890 |
+
"step": 3550
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 4.08,
|
| 894 |
+
"learning_rate": 3.1822222222222226e-06,
|
| 895 |
+
"loss": 2.7826,
|
| 896 |
+
"step": 3575
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 4.09,
|
| 900 |
+
"learning_rate": 3.1266666666666667e-06,
|
| 901 |
+
"loss": 2.9641,
|
| 902 |
+
"step": 3600
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 4.09,
|
| 906 |
+
"learning_rate": 3.0711111111111115e-06,
|
| 907 |
+
"loss": 2.8948,
|
| 908 |
+
"step": 3625
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 4.1,
|
| 912 |
+
"learning_rate": 3.015555555555556e-06,
|
| 913 |
+
"loss": 2.8519,
|
| 914 |
+
"step": 3650
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 4.1,
|
| 918 |
+
"learning_rate": 2.96e-06,
|
| 919 |
+
"loss": 2.8796,
|
| 920 |
+
"step": 3675
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 4.11,
|
| 924 |
+
"learning_rate": 2.904444444444445e-06,
|
| 925 |
+
"loss": 2.9119,
|
| 926 |
+
"step": 3700
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 4.11,
|
| 930 |
+
"learning_rate": 2.8488888888888894e-06,
|
| 931 |
+
"loss": 2.8479,
|
| 932 |
+
"step": 3725
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 4.12,
|
| 936 |
+
"learning_rate": 2.7933333333333334e-06,
|
| 937 |
+
"loss": 2.9925,
|
| 938 |
+
"step": 3750
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 4.12,
|
| 942 |
+
"learning_rate": 2.7377777777777783e-06,
|
| 943 |
+
"loss": 2.9697,
|
| 944 |
+
"step": 3775
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 4.13,
|
| 948 |
+
"learning_rate": 2.6822222222222223e-06,
|
| 949 |
+
"loss": 2.9331,
|
| 950 |
+
"step": 3800
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 4.13,
|
| 954 |
+
"learning_rate": 2.6266666666666668e-06,
|
| 955 |
+
"loss": 2.7614,
|
| 956 |
+
"step": 3825
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 4.14,
|
| 960 |
+
"learning_rate": 2.5711111111111112e-06,
|
| 961 |
+
"loss": 2.9913,
|
| 962 |
+
"step": 3850
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 4.14,
|
| 966 |
+
"learning_rate": 2.5155555555555557e-06,
|
| 967 |
+
"loss": 2.8217,
|
| 968 |
+
"step": 3875
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 4.15,
|
| 972 |
+
"learning_rate": 2.46e-06,
|
| 973 |
+
"loss": 2.7742,
|
| 974 |
+
"step": 3900
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 4.15,
|
| 978 |
+
"learning_rate": 2.4044444444444446e-06,
|
| 979 |
+
"loss": 2.8652,
|
| 980 |
+
"step": 3925
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 5.0,
|
| 984 |
+
"learning_rate": 2.348888888888889e-06,
|
| 985 |
+
"loss": 2.9482,
|
| 986 |
+
"step": 3950
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 5.01,
|
| 990 |
+
"learning_rate": 2.2933333333333335e-06,
|
| 991 |
+
"loss": 2.7808,
|
| 992 |
+
"step": 3975
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 5.01,
|
| 996 |
+
"learning_rate": 2.237777777777778e-06,
|
| 997 |
+
"loss": 2.8327,
|
| 998 |
+
"step": 4000
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 5.01,
|
| 1002 |
+
"eval_cer": 333.05161485058863,
|
| 1003 |
+
"eval_loss": 3.225778102874756,
|
| 1004 |
+
"eval_runtime": 362.3621,
|
| 1005 |
+
"eval_samples_per_second": 2.721,
|
| 1006 |
+
"eval_steps_per_second": 1.361,
|
| 1007 |
+
"eval_wer": 327.9083969465649,
|
| 1008 |
+
"step": 4000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 5.02,
|
| 1012 |
+
"learning_rate": 2.1822222222222225e-06,
|
| 1013 |
+
"loss": 2.7936,
|
| 1014 |
+
"step": 4025
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 5.02,
|
| 1018 |
+
"learning_rate": 2.126666666666667e-06,
|
| 1019 |
+
"loss": 2.7693,
|
| 1020 |
+
"step": 4050
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 5.03,
|
| 1024 |
+
"learning_rate": 2.0711111111111114e-06,
|
| 1025 |
+
"loss": 2.7341,
|
| 1026 |
+
"step": 4075
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 5.03,
|
| 1030 |
+
"learning_rate": 2.0155555555555554e-06,
|
| 1031 |
+
"loss": 2.7995,
|
| 1032 |
+
"step": 4100
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 5.04,
|
| 1036 |
+
"learning_rate": 1.9600000000000003e-06,
|
| 1037 |
+
"loss": 2.78,
|
| 1038 |
+
"step": 4125
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 5.04,
|
| 1042 |
+
"learning_rate": 1.9044444444444445e-06,
|
| 1043 |
+
"loss": 2.8048,
|
| 1044 |
+
"step": 4150
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 5.05,
|
| 1048 |
+
"learning_rate": 1.848888888888889e-06,
|
| 1049 |
+
"loss": 2.6663,
|
| 1050 |
+
"step": 4175
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 5.05,
|
| 1054 |
+
"learning_rate": 1.7933333333333337e-06,
|
| 1055 |
+
"loss": 2.9016,
|
| 1056 |
+
"step": 4200
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 5.06,
|
| 1060 |
+
"learning_rate": 1.737777777777778e-06,
|
| 1061 |
+
"loss": 2.7117,
|
| 1062 |
+
"step": 4225
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 5.06,
|
| 1066 |
+
"learning_rate": 1.6822222222222224e-06,
|
| 1067 |
+
"loss": 2.6716,
|
| 1068 |
+
"step": 4250
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 5.07,
|
| 1072 |
+
"learning_rate": 1.6266666666666666e-06,
|
| 1073 |
+
"loss": 2.7193,
|
| 1074 |
+
"step": 4275
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 5.07,
|
| 1078 |
+
"learning_rate": 1.5711111111111113e-06,
|
| 1079 |
+
"loss": 2.7704,
|
| 1080 |
+
"step": 4300
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 5.08,
|
| 1084 |
+
"learning_rate": 1.5155555555555558e-06,
|
| 1085 |
+
"loss": 2.9998,
|
| 1086 |
+
"step": 4325
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 5.08,
|
| 1090 |
+
"learning_rate": 1.46e-06,
|
| 1091 |
+
"loss": 2.8433,
|
| 1092 |
+
"step": 4350
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 5.09,
|
| 1096 |
+
"learning_rate": 1.4044444444444447e-06,
|
| 1097 |
+
"loss": 2.6071,
|
| 1098 |
+
"step": 4375
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 5.09,
|
| 1102 |
+
"learning_rate": 1.3488888888888891e-06,
|
| 1103 |
+
"loss": 2.8095,
|
| 1104 |
+
"step": 4400
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 5.1,
|
| 1108 |
+
"learning_rate": 1.2933333333333334e-06,
|
| 1109 |
+
"loss": 2.6704,
|
| 1110 |
+
"step": 4425
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 5.1,
|
| 1114 |
+
"learning_rate": 1.2377777777777778e-06,
|
| 1115 |
+
"loss": 2.6676,
|
| 1116 |
+
"step": 4450
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 5.11,
|
| 1120 |
+
"learning_rate": 1.1822222222222223e-06,
|
| 1121 |
+
"loss": 2.8023,
|
| 1122 |
+
"step": 4475
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 5.11,
|
| 1126 |
+
"learning_rate": 1.1266666666666667e-06,
|
| 1127 |
+
"loss": 2.7526,
|
| 1128 |
+
"step": 4500
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 5.12,
|
| 1132 |
+
"learning_rate": 1.0711111111111112e-06,
|
| 1133 |
+
"loss": 2.7228,
|
| 1134 |
+
"step": 4525
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 5.12,
|
| 1138 |
+
"learning_rate": 1.0155555555555557e-06,
|
| 1139 |
+
"loss": 2.6382,
|
| 1140 |
+
"step": 4550
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 5.13,
|
| 1144 |
+
"learning_rate": 9.600000000000001e-07,
|
| 1145 |
+
"loss": 2.7358,
|
| 1146 |
+
"step": 4575
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 5.13,
|
| 1150 |
+
"learning_rate": 9.044444444444445e-07,
|
| 1151 |
+
"loss": 2.6922,
|
| 1152 |
+
"step": 4600
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 5.14,
|
| 1156 |
+
"learning_rate": 8.488888888888889e-07,
|
| 1157 |
+
"loss": 2.847,
|
| 1158 |
+
"step": 4625
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 5.14,
|
| 1162 |
+
"learning_rate": 7.933333333333335e-07,
|
| 1163 |
+
"loss": 2.6146,
|
| 1164 |
+
"step": 4650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 5.15,
|
| 1168 |
+
"learning_rate": 7.377777777777779e-07,
|
| 1169 |
+
"loss": 2.7914,
|
| 1170 |
+
"step": 4675
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 5.15,
|
| 1174 |
+
"learning_rate": 6.822222222222223e-07,
|
| 1175 |
+
"loss": 2.645,
|
| 1176 |
+
"step": 4700
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 5.16,
|
| 1180 |
+
"learning_rate": 6.266666666666667e-07,
|
| 1181 |
+
"loss": 2.717,
|
| 1182 |
+
"step": 4725
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 6.0,
|
| 1186 |
+
"learning_rate": 5.711111111111111e-07,
|
| 1187 |
+
"loss": 2.751,
|
| 1188 |
+
"step": 4750
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 6.01,
|
| 1192 |
+
"learning_rate": 5.155555555555556e-07,
|
| 1193 |
+
"loss": 2.6859,
|
| 1194 |
+
"step": 4775
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 6.01,
|
| 1198 |
+
"learning_rate": 4.6000000000000004e-07,
|
| 1199 |
+
"loss": 2.4752,
|
| 1200 |
+
"step": 4800
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 6.02,
|
| 1204 |
+
"learning_rate": 4.0444444444444445e-07,
|
| 1205 |
+
"loss": 2.6502,
|
| 1206 |
+
"step": 4825
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 6.02,
|
| 1210 |
+
"learning_rate": 3.488888888888889e-07,
|
| 1211 |
+
"loss": 2.5226,
|
| 1212 |
+
"step": 4850
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 6.03,
|
| 1216 |
+
"learning_rate": 2.9333333333333337e-07,
|
| 1217 |
+
"loss": 2.6241,
|
| 1218 |
+
"step": 4875
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 6.03,
|
| 1222 |
+
"learning_rate": 2.3777777777777777e-07,
|
| 1223 |
+
"loss": 2.5514,
|
| 1224 |
+
"step": 4900
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 6.04,
|
| 1228 |
+
"learning_rate": 1.8222222222222226e-07,
|
| 1229 |
+
"loss": 2.6996,
|
| 1230 |
+
"step": 4925
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 6.04,
|
| 1234 |
+
"learning_rate": 1.2666666666666666e-07,
|
| 1235 |
+
"loss": 2.6358,
|
| 1236 |
+
"step": 4950
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 6.05,
|
| 1240 |
+
"learning_rate": 7.111111111111112e-08,
|
| 1241 |
+
"loss": 2.7597,
|
| 1242 |
+
"step": 4975
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 6.05,
|
| 1246 |
+
"learning_rate": 1.5555555555555557e-08,
|
| 1247 |
+
"loss": 2.6468,
|
| 1248 |
+
"step": 5000
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 6.05,
|
| 1252 |
+
"eval_cer": 123.45306368849984,
|
| 1253 |
+
"eval_loss": 3.212874174118042,
|
| 1254 |
+
"eval_runtime": 302.4073,
|
| 1255 |
+
"eval_samples_per_second": 3.261,
|
| 1256 |
+
"eval_steps_per_second": 1.63,
|
| 1257 |
+
"eval_wer": 118.50381679389312,
|
| 1258 |
+
"step": 5000
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 6.05,
|
| 1262 |
+
"step": 5000,
|
| 1263 |
+
"total_flos": 2.12189711818752e+19,
|
| 1264 |
+
"train_loss": 3.0522214595794677,
|
| 1265 |
+
"train_runtime": 5458.8622,
|
| 1266 |
+
"train_samples_per_second": 1.832,
|
| 1267 |
+
"train_steps_per_second": 0.916
|
| 1268 |
+
}
|
| 1269 |
+
],
|
| 1270 |
+
"max_steps": 5000,
|
| 1271 |
+
"num_train_epochs": 9223372036854775807,
|
| 1272 |
+
"total_flos": 2.12189711818752e+19,
|
| 1273 |
+
"trial_name": null,
|
| 1274 |
+
"trial_params": null
|
| 1275 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0917c506d33e6aaecd26c5c143567a69a21ec072808d7d6a3e64a1189180b2d
|
| 3 |
+
size 3515
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|