Upload tokenizer
Browse files- added_tokens.json +1 -3
- special_tokens_map.json +2 -2
- tokenizer_config.json +2 -18
added_tokens.json
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
{
|
| 2 |
"</s>": 111,
|
| 3 |
-
"<s>": 110
|
| 4 |
-
"[PAD]": 113,
|
| 5 |
-
"[UNK]": 112
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"</s>": 111,
|
| 3 |
+
"<s>": 110
|
|
|
|
|
|
|
| 4 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
-
"pad_token": "
|
| 5 |
-
"unk_token": "
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
}
|
tokenizer_config.json
CHANGED
|
@@ -31,22 +31,6 @@
|
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
-
},
|
| 35 |
-
"112": {
|
| 36 |
-
"content": "[UNK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
},
|
| 43 |
-
"113": {
|
| 44 |
-
"content": "[PAD]",
|
| 45 |
-
"lstrip": false,
|
| 46 |
-
"normalized": false,
|
| 47 |
-
"rstrip": false,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": true
|
| 50 |
}
|
| 51 |
},
|
| 52 |
"bos_token": "<s>",
|
|
@@ -54,10 +38,10 @@
|
|
| 54 |
"do_lower_case": false,
|
| 55 |
"eos_token": "</s>",
|
| 56 |
"model_max_length": 1000000000000000019884624838656,
|
| 57 |
-
"pad_token": "
|
| 58 |
"replace_word_delimiter_char": " ",
|
| 59 |
"target_lang": null,
|
| 60 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 61 |
-
"unk_token": "
|
| 62 |
"word_delimiter_token": "|"
|
| 63 |
}
|
|
|
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
}
|
| 35 |
},
|
| 36 |
"bos_token": "<s>",
|
|
|
|
| 38 |
"do_lower_case": false,
|
| 39 |
"eos_token": "</s>",
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
+
"pad_token": "<pad>",
|
| 42 |
"replace_word_delimiter_char": " ",
|
| 43 |
"target_lang": null,
|
| 44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 45 |
+
"unk_token": "<unk>",
|
| 46 |
"word_delimiter_token": "|"
|
| 47 |
}
|