Commit
•
258cc7f
1
Parent(s):
b0cce44
Upload tokenizer
Browse files- special_tokens_map.json +28 -4
- tokenizer_config.json +1 -0
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,30 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": true,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": true,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "[UNK]",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": true,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
}
|
tokenizer_config.json
CHANGED
|
@@ -39,6 +39,7 @@
|
|
| 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",
|
|
|
|
| 39 |
"eos_token": "</s>",
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
"pad_token": "[PAD]",
|
| 42 |
+
"processor_class": "Wav2Vec2Processor",
|
| 43 |
"replace_word_delimiter_char": " ",
|
| 44 |
"target_lang": null,
|
| 45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|