Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +13 -0
- vocab.json +41 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"unk_token": "[UNK]"
|
| 6 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"replace_word_delimiter_char": " ",
|
| 9 |
+
"target_lang": null,
|
| 10 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 11 |
+
"unk_token": "[UNK]",
|
| 12 |
+
"word_delimiter_token": "|"
|
| 13 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 38,
|
| 3 |
+
"[UNK]": 37,
|
| 4 |
+
"a": 33,
|
| 5 |
+
"b": 19,
|
| 6 |
+
"c": 20,
|
| 7 |
+
"e": 0,
|
| 8 |
+
"f": 5,
|
| 9 |
+
"g": 23,
|
| 10 |
+
"j": 18,
|
| 11 |
+
"k": 28,
|
| 12 |
+
"l": 34,
|
| 13 |
+
"m": 15,
|
| 14 |
+
"o": 1,
|
| 15 |
+
"q": 26,
|
| 16 |
+
"r": 10,
|
| 17 |
+
"t": 32,
|
| 18 |
+
"u": 29,
|
| 19 |
+
"w": 31,
|
| 20 |
+
"x": 27,
|
| 21 |
+
"y": 25,
|
| 22 |
+
"z": 4,
|
| 23 |
+
"|": 35,
|
| 24 |
+
"ĉ": 13,
|
| 25 |
+
"č": 24,
|
| 26 |
+
"ğ": 36,
|
| 27 |
+
"ţ": 7,
|
| 28 |
+
"ǧ": 22,
|
| 29 |
+
"ɛ": 17,
|
| 30 |
+
"ɣ": 30,
|
| 31 |
+
"̣": 11,
|
| 32 |
+
"γ": 14,
|
| 33 |
+
"ε": 6,
|
| 34 |
+
"ԑ": 9,
|
| 35 |
+
"ḍ": 12,
|
| 36 |
+
"ḥ": 2,
|
| 37 |
+
"ṛ": 21,
|
| 38 |
+
"ṣ": 8,
|
| 39 |
+
"ṭ": 3,
|
| 40 |
+
"ẓ": 16
|
| 41 |
+
}
|