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 |
+
{"O": 0, "R": 1, "f": 2, "y": 3, "I": 4, "p": 5, "\"": 6, "?": 7, "M": 8, "X": 9, "S": 10, "n": 12, "H": 13, "C": 14, "e": 15, "U": 16, "u": 17, "-": 18, "k": 19, ",": 20, "'": 21, "q": 22, "d": 23, "a": 24, "v": 25, "j": 26, ":": 27, "K": 28, "s": 29, "i": 30, "t": 31, "h": 32, "z": 33, "b": 34, "c": 35, "!": 36, "J": 37, "V": 38, "E": 39, "m": 40, "l": 41, "w": 42, "Y": 43, ".": 44, "N": 45, "A": 46, "T": 47, "x": 48, ";": 49, "D": 50, "r": 51, "F": 52, "W": 53, "B": 54, "Q": 55, "o": 56, "g": 57, "G": 58, "P": 59, "L": 60, "|": 11, "[UNK]": 61, "[PAD]": 62, "<s>": 63, "</s>": 64}
|