add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"th": 0, "hh": 1, "iy": 2, "h#": 3, "ah": 4, "ng": 5, "ow": 6, "axr": 7, "ax-h": 8, "pcl": 9, "en": 10, "dcl": 11, "dx": 12, "f": 13, "t": 14, "n": 15, "aa": 16, "gcl": 17, "sh": 18, "oy": 19, "b": 20, "m": 21, "dh": 22, "pau": 23, "nx": 24, "kcl": 25, "ey": 26, "s": 27, "zh": 28, "k": 29, "uw": 30, "em": 31, "ae": 32, "ux": 33, "el": 34, "v": 35, "jh": 36, "tcl": 37, "w": 38, "g": 39, "d": 40, "l": 41, "epi": 42, "hv": 43, "bcl": 44, "ix": 45, "er": 46, "r": 47, "ch": 48, "p": 49, "ao": 50, "y": 51, "aw": 52, "eh": 53, "q": 54, "z": 55, "eng": 56, "ay": 57, "ih": 58, "uh": 59, "ax": 60, "[UNK]": 61, "[PAD]": 62}
|