Commit
•
269d525
1
Parent(s):
538d309
Upload tokenizer
Browse files- tokenizer_config.json +3 -0
tokenizer_config.json
CHANGED
|
@@ -1,9 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
|
|
|
| 3 |
"do_lower_case": false,
|
| 4 |
"eos_token": "</s>",
|
|
|
|
| 5 |
"pad_token": "[PAD]",
|
| 6 |
"replace_word_delimiter_char": " ",
|
|
|
|
| 7 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 8 |
"unk_token": "[UNK]",
|
| 9 |
"word_delimiter_token": "|"
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
"do_lower_case": false,
|
| 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",
|
| 11 |
"unk_token": "[UNK]",
|
| 12 |
"word_delimiter_token": "|"
|