add tokenizer
Browse files- .gitignore +1 -0
- added_tokens.json +1 -4
- special_tokens_map.json +1 -22
- tokenizer_config.json +1 -12
- vocab.json +1 -38
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
added_tokens.json
CHANGED
|
@@ -1,4 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"</s>": 37,
|
| 3 |
-
"<s>": 36
|
| 4 |
-
}
|
|
|
|
| 1 |
+
{"<s>": 36, "</s>": 37}
|
|
|
|
|
|
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,22 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
{
|
| 4 |
-
"content": "<s>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": true,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"content": "</s>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": true,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
}
|
| 17 |
-
],
|
| 18 |
-
"bos_token": "<s>",
|
| 19 |
-
"eos_token": "</s>",
|
| 20 |
-
"pad_token": "[PAD]",
|
| 21 |
-
"unk_token": "[UNK]"
|
| 22 |
-
}
|
|
|
|
| 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
CHANGED
|
@@ -1,12 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
-
"do_lower_case": false,
|
| 4 |
-
"eos_token": "</s>",
|
| 5 |
-
"name_or_path": "./",
|
| 6 |
-
"pad_token": "[PAD]",
|
| 7 |
-
"replace_word_delimiter_char": " ",
|
| 8 |
-
"special_tokens_map_file": null,
|
| 9 |
-
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 10 |
-
"unk_token": "[UNK]",
|
| 11 |
-
"word_delimiter_token": "|"
|
| 12 |
-
}
|
|
|
|
| 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": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vocab.json
CHANGED
|
@@ -1,38 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"[PAD]": 35,
|
| 3 |
-
"[UNK]": 34,
|
| 4 |
-
"a": 1,
|
| 5 |
-
"b": 2,
|
| 6 |
-
"c": 3,
|
| 7 |
-
"d": 4,
|
| 8 |
-
"e": 5,
|
| 9 |
-
"f": 6,
|
| 10 |
-
"g": 7,
|
| 11 |
-
"h": 8,
|
| 12 |
-
"i": 9,
|
| 13 |
-
"j": 10,
|
| 14 |
-
"k": 11,
|
| 15 |
-
"l": 12,
|
| 16 |
-
"m": 13,
|
| 17 |
-
"n": 14,
|
| 18 |
-
"o": 15,
|
| 19 |
-
"p": 16,
|
| 20 |
-
"q": 17,
|
| 21 |
-
"r": 18,
|
| 22 |
-
"s": 19,
|
| 23 |
-
"t": 20,
|
| 24 |
-
"u": 21,
|
| 25 |
-
"v": 22,
|
| 26 |
-
"w": 23,
|
| 27 |
-
"x": 24,
|
| 28 |
-
"y": 25,
|
| 29 |
-
"z": 26,
|
| 30 |
-
"|": 0,
|
| 31 |
-
"á": 27,
|
| 32 |
-
"é": 28,
|
| 33 |
-
"í": 29,
|
| 34 |
-
"ñ": 30,
|
| 35 |
-
"ó": 31,
|
| 36 |
-
"ú": 32,
|
| 37 |
-
"ü": 33
|
| 38 |
-
}
|
|
|
|
| 1 |
+
{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "á": 27, "é": 28, "í": 29, "ñ": 30, "ó": 31, "ú": 32, "ü": 33, "|": 0, "[UNK]": 34, "[PAD]": 35}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|