Upload processor
Browse files- preprocessor_config.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
- vocab.json +0 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 80,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "WhisperProcessor",
|
| 13 |
+
"return_attention_mask": false,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -972,9 +972,16 @@
|
|
| 972 |
"eos_token": "<|endoftext|>",
|
| 973 |
"errors": "replace",
|
| 974 |
"extra_special_tokens": {},
|
|
|
|
| 975 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 976 |
"pad_token": "<|endoftext|>",
|
|
|
|
|
|
|
| 977 |
"processor_class": "WhisperProcessor",
|
|
|
|
| 978 |
"tokenizer_class": "WhisperTokenizer",
|
|
|
|
|
|
|
| 979 |
"unk_token": "<|endoftext|>"
|
| 980 |
}
|
|
|
|
| 972 |
"eos_token": "<|endoftext|>",
|
| 973 |
"errors": "replace",
|
| 974 |
"extra_special_tokens": {},
|
| 975 |
+
"max_length": 448,
|
| 976 |
"model_max_length": 1000000000000000019884624838656,
|
| 977 |
+
"pad_to_multiple_of": null,
|
| 978 |
"pad_token": "<|endoftext|>",
|
| 979 |
+
"pad_token_type_id": 0,
|
| 980 |
+
"padding_side": "right",
|
| 981 |
"processor_class": "WhisperProcessor",
|
| 982 |
+
"stride": 0,
|
| 983 |
"tokenizer_class": "WhisperTokenizer",
|
| 984 |
+
"truncation_side": "right",
|
| 985 |
+
"truncation_strategy": "longest_first",
|
| 986 |
"unk_token": "<|endoftext|>"
|
| 987 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|