Commit
•
0868a49
1
Parent(s):
6a54174
Upload processor
Browse files- preprocessor_config.json +11 -0
- tokenizer_config.json +3 -2
preprocessor_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"feature_extractor_type": "SeamlessM4TFeatureExtractor",
|
| 3 |
+
"feature_size": 80,
|
| 4 |
+
"num_mel_bins": 80,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2BertProcessor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000,
|
| 10 |
+
"stride": 2
|
| 11 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -19,7 +19,7 @@
|
|
| 19 |
"72": {
|
| 20 |
"content": "<s>",
|
| 21 |
"lstrip": false,
|
| 22 |
-
"normalized":
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
|
@@ -27,7 +27,7 @@
|
|
| 27 |
"73": {
|
| 28 |
"content": "</s>",
|
| 29 |
"lstrip": false,
|
| 30 |
-
"normalized":
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
|
@@ -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",
|
|
|
|
| 19 |
"72": {
|
| 20 |
"content": "<s>",
|
| 21 |
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
|
|
|
| 27 |
"73": {
|
| 28 |
"content": "</s>",
|
| 29 |
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
|
|
|
| 39 |
"eos_token": "</s>",
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
"pad_token": "[PAD]",
|
| 42 |
+
"processor_class": "Wav2Vec2BertProcessor",
|
| 43 |
"replace_word_delimiter_char": " ",
|
| 44 |
"target_lang": null,
|
| 45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|