Upload tokenizer

README.md

@@ -1,18 +1,18 @@
 ---
-license: apache-2.0
 base_model: facebook/wav2vec2-base
-tags:
-- generated_from_trainer
 datasets:
 - vivos
+license: apache-2.0
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: wav2vec2-vivos
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: vivos
       type: vivos
@@ -20,9 +20,9 @@ model-index:
       split: None
       args: default
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.2558154859967051
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 93,
+  "<s>": 92
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "90": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "93": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,94 @@
+{
+  "[PAD]": 91,
+  "[UNK]": 90,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "g": 6,
+  "h": 7,
+  "i": 8,
+  "k": 9,
+  "l": 10,
+  "m": 11,
+  "n": 12,
+  "o": 13,
+  "p": 14,
+  "q": 15,
+  "r": 16,
+  "s": 17,
+  "t": 18,
+  "u": 19,
+  "v": 20,
+  "x": 21,
+  "y": 22,
+  "|": 0,
+  "à": 23,
+  "á": 24,
+  "â": 25,
+  "ã": 26,
+  "è": 27,
+  "é": 28,
+  "ê": 29,
+  "ì": 30,
+  "í": 31,
+  "ò": 32,
+  "ó": 33,
+  "ô": 34,
+  "õ": 35,
+  "ù": 36,
+  "ú": 37,
+  "ý": 38,
+  "ă": 39,
+  "đ": 40,
+  "ĩ": 41,
+  "ũ": 42,
+  "ơ": 43,
+  "ư": 44,
+  "ạ": 45,
+  "ả": 46,
+  "ấ": 47,
+  "ầ": 48,
+  "ẩ": 49,
+  "ẫ": 50,
+  "ậ": 51,
+  "ắ": 52,
+  "ằ": 53,
+  "ẳ": 54,
+  "ẵ": 55,
+  "ặ": 56,
+  "ẹ": 57,
+  "ẻ": 58,
+  "ẽ": 59,
+  "ế": 60,
+  "ề": 61,
+  "ể": 62,
+  "ễ": 63,
+  "ệ": 64,
+  "ỉ": 65,
+  "ị": 66,
+  "ọ": 67,
+  "ỏ": 68,
+  "ố": 69,
+  "ồ": 70,
+  "ổ": 71,
+  "ỗ": 72,
+  "ộ": 73,
+  "ớ": 74,
+  "ờ": 75,
+  "ở": 76,
+  "ỡ": 77,
+  "ợ": 78,
+  "ụ": 79,
+  "ủ": 80,
+  "ứ": 81,
+  "ừ": 82,
+  "ử": 83,
+  "ữ": 84,
+  "ự": 85,
+  "ỳ": 86,
+  "ỵ": 87,
+  "ỷ": 88,
+  "ỹ": 89
+}