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 |
+
{"aa": 1, "ae": 2, "ah": 3, "ao": 4, "aw": 5, "ax": 6, "ax-h": 7, "axr": 8, "ay": 9, "b": 10, "bcl": 11, "ch": 12, "d": 13, "dcl": 14, "dh": 15, "dx": 16, "eh": 17, "el": 18, "em": 19, "en": 20, "eng": 21, "epi": 22, "er": 23, "ey": 24, "f": 25, "g": 26, "gcl": 27, "h#": 28, "hh": 29, "hv": 30, "ih": 31, "ix": 32, "iy": 33, "jh": 34, "k": 35, "kcl": 36, "l": 37, "m": 38, "n": 39, "ng": 40, "nx": 41, "ow": 42, "oy": 43, "p": 44, "pau": 45, "pcl": 46, "q": 47, "r": 48, "s": 49, "sh": 50, "t": 51, "tcl": 52, "th": 53, "uh": 54, "uw": 55, "ux": 56, "v": 57, "w": 58, "y": 59, "z": 60, "zh": 61, "|": 0, "[UNK]": 62, "[PAD]": 63}
|