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