Upload tokenizer
Browse files- special_tokens_map.json +0 -14
- tokenizer_config.json +0 -1
special_tokens_map.json
CHANGED
|
@@ -1,19 +1,5 @@
|
|
| 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 |
"content": "<s>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
{
|
| 4 |
"content": "<s>",
|
| 5 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -5,7 +5,6 @@
|
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
-
"processor_class": "Wav2Vec2ProcessorWithLM",
|
| 9 |
"replace_word_delimiter_char": " ",
|
| 10 |
"target_lang": null,
|
| 11 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"pad_token": "[PAD]",
|
|
|
|
| 8 |
"replace_word_delimiter_char": " ",
|
| 9 |
"target_lang": null,
|
| 10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|