add files
Browse files- tokenizer_config.json +1 -0
- vocab.json +1 -0
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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/workspace/container_0/model/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"aa": 1, "ae": 2, "ah": 3, "aw": 4, "ax": 5, "axr": 6, "ay": 7, "b": 8, "ch": 9, "d": 10, "dh": 11, "dx": 12, "eh": 13, "el": 14, "em": 15, "en": 16, "eng": 17, "er": 18, "ey": 19, "f": 20, "g": 21, "h#": 22, "hh": 23, "hv": 24, "ih": 25, "ix": 26, "iy": 27, "jh": 28, "k": 29, "l": 30, "m": 31, "n": 32, "ng": 33, "nx": 34, "ow": 35, "oy": 36, "p": 37, "q": 38, "r": 39, "s": 40, "sh": 41, "t": 42, "th": 43, "uh": 44, "uw": 45, "v": 46, "w": 47, "y": 48, "z": 49, "zh": 50, "|": 0, "[UNK]": 51, "[PAD]": 52}
|