add tokenizer
Browse files- added_tokens.json +1 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<s>": 43, "</s>": 44}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
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/arctic_model/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"aa": 1, "ae": 2, "ah": 3, "aw": 4, "ay": 5, "b": 6, "ch": 7, "d": 8, "dh": 9, "dx": 10, "eh": 11, "er": 12, "ey": 13, "f": 14, "g": 15, "h#": 16, "hh": 17, "ih": 18, "iy": 19, "jh": 20, "k": 21, "l": 22, "m": 23, "n": 24, "ng": 25, "ow": 26, "oy": 27, "p": 28, "r": 29, "s": 30, "sh": 31, "spn": 32, "t": 33, "th": 34, "uh": 35, "uw": 36, "v": 37, "w": 38, "y": 39, "z": 40, "|": 0, "[UNK]": 41, "[PAD]": 42}
|