Bakht Ullah
commited on
Commit
·
7e57e79
1
Parent(s):
e7eb8e8
Upload tokenizer
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -9,6 +9,7 @@
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 12 |
"eos_token": {
|
| 13 |
"__type": "AddedToken",
|
| 14 |
"content": "<|endoftext|>",
|
|
@@ -22,7 +23,6 @@
|
|
| 22 |
"pad_token": null,
|
| 23 |
"processor_class": "WhisperProcessor",
|
| 24 |
"return_attention_mask": false,
|
| 25 |
-
"special_tokens_map_file": null,
|
| 26 |
"tokenizer_class": "WhisperTokenizer",
|
| 27 |
"unk_token": {
|
| 28 |
"__type": "AddedToken",
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "<|endoftext|>",
|
|
|
|
| 23 |
"pad_token": null,
|
| 24 |
"processor_class": "WhisperProcessor",
|
| 25 |
"return_attention_mask": false,
|
|
|
|
| 26 |
"tokenizer_class": "WhisperTokenizer",
|
| 27 |
"unk_token": {
|
| 28 |
"__type": "AddedToken",
|