Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +10 -0
- vocab.json +46 -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 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"do_lower_case": false,
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"pad_token": "[PAD]",
|
| 6 |
+
"replace_word_delimiter_char": " ",
|
| 7 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 8 |
+
"unk_token": "[UNK]",
|
| 9 |
+
"word_delimiter_token": "|"
|
| 10 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"'": 13,
|
| 3 |
+
"[PAD]": 43,
|
| 4 |
+
"[UNK]": 42,
|
| 5 |
+
"a": 17,
|
| 6 |
+
"b": 24,
|
| 7 |
+
"c": 29,
|
| 8 |
+
"d": 5,
|
| 9 |
+
"e": 18,
|
| 10 |
+
"f": 40,
|
| 11 |
+
"g": 26,
|
| 12 |
+
"h": 11,
|
| 13 |
+
"i": 0,
|
| 14 |
+
"j": 2,
|
| 15 |
+
"k": 12,
|
| 16 |
+
"l": 21,
|
| 17 |
+
"m": 14,
|
| 18 |
+
"n": 22,
|
| 19 |
+
"o": 34,
|
| 20 |
+
"p": 38,
|
| 21 |
+
"q": 23,
|
| 22 |
+
"r": 41,
|
| 23 |
+
"s": 33,
|
| 24 |
+
"t": 8,
|
| 25 |
+
"u": 9,
|
| 26 |
+
"v": 36,
|
| 27 |
+
"w": 7,
|
| 28 |
+
"x": 19,
|
| 29 |
+
"y": 28,
|
| 30 |
+
"z": 10,
|
| 31 |
+
"|": 15,
|
| 32 |
+
"à": 35,
|
| 33 |
+
"á": 30,
|
| 34 |
+
"â": 39,
|
| 35 |
+
"ã": 20,
|
| 36 |
+
"ç": 1,
|
| 37 |
+
"é": 3,
|
| 38 |
+
"ê": 4,
|
| 39 |
+
"í": 37,
|
| 40 |
+
"ñ": 31,
|
| 41 |
+
"ó": 32,
|
| 42 |
+
"ô": 16,
|
| 43 |
+
"õ": 27,
|
| 44 |
+
"ú": 6,
|
| 45 |
+
"ü": 25
|
| 46 |
+
}
|