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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"v": 0, "y": 1, "o": 2, "b": 3, "r": 5, "m": 6, "d": 7, "f": 8, "u": 9, "c": 10, "j": 11, "t": 12, "'": 13, "w": 14, "p": 15, "g": 16, "q": 17, "z": 18, "l": 19, "i": 20, "a": 21, "n": 22, "e": 23, "h": 24, "s": 25, "x": 26, "k": 27, "|": 4, "[UNK]": 28, "[PAD]": 29}
|