Upload tokenizer
Browse files- tokenizer_config.json +31 -0
tokenizer_config.json
CHANGED
|
@@ -43,5 +43,36 @@
|
|
| 43 |
"target_lang": null,
|
| 44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 45 |
"unk_token": "[UNK]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
"word_delimiter_token": "|"
|
| 47 |
}
|
|
|
|
| 43 |
"target_lang": null,
|
| 44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 45 |
"unk_token": "[UNK]",
|
| 46 |
+
"vocab_dict": {
|
| 47 |
+
"[PAD]": 28,
|
| 48 |
+
"[UNK]": 27,
|
| 49 |
+
"a": 1,
|
| 50 |
+
"b": 2,
|
| 51 |
+
"c": 3,
|
| 52 |
+
"d": 4,
|
| 53 |
+
"e": 5,
|
| 54 |
+
"f": 6,
|
| 55 |
+
"g": 7,
|
| 56 |
+
"h": 8,
|
| 57 |
+
"i": 9,
|
| 58 |
+
"j": 10,
|
| 59 |
+
"k": 11,
|
| 60 |
+
"l": 12,
|
| 61 |
+
"m": 13,
|
| 62 |
+
"n": 14,
|
| 63 |
+
"o": 15,
|
| 64 |
+
"p": 16,
|
| 65 |
+
"q": 17,
|
| 66 |
+
"r": 18,
|
| 67 |
+
"s": 19,
|
| 68 |
+
"t": 20,
|
| 69 |
+
"u": 21,
|
| 70 |
+
"v": 22,
|
| 71 |
+
"w": 23,
|
| 72 |
+
"x": 24,
|
| 73 |
+
"y": 25,
|
| 74 |
+
"z": 26,
|
| 75 |
+
"|": 0
|
| 76 |
+
},
|
| 77 |
"word_delimiter_token": "|"
|
| 78 |
}
|