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 |
+
{"ð": 0, "ɨ": 1, "ʊ": 2, "s": 3, "b": 4, "ʌ": 5, "J": 6, "p": 7, "l": 8, "d": 9, "æ": 10, "n": 11, "g": 12, "e": 13, "ʔ": 14, "P": 15, "C": 16, "ʒ": 17, "ɹ": 18, "i": 19, "ɝ": 21, "ɪ": 22, "ɦ": 23, "t": 24, "̩": 25, "ɔ": 26, "̚": 27, "̃": 28, "ɡ": 29, "u": 30, "o": 31, "z": 32, "h": 33, "ɑ": 34, "θ": 35, "j": 36, "ɚ": 37, "W": 38, "O": 39, "m": 40, "̍": 41, "ɛ": 42, "ŋ": 43, "k": 44, "̥": 45, "ə": 46, "Y": 47, "S": 48, "ʉ": 49, "w": 50, "ɾ": 51, "ʃ": 52, "f": 53, "v": 54, "|": 20, "[UNK]": 55, "[PAD]": 56}
|