BaseLayer commited on
Commit
7d26614
·
verified ·
1 Parent(s): 652e62c

Upload processor

Browse files
Files changed (3) hide show
  1. processor_config.json +17 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +19 -0
processor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "chunk_length": 30,
4
+ "dither": 0.0,
5
+ "feature_extractor_type": "WhisperFeatureExtractor",
6
+ "feature_size": 80,
7
+ "hop_length": 160,
8
+ "n_fft": 400,
9
+ "n_samples": 480000,
10
+ "nb_max_frames": 3000,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "return_attention_mask": false,
14
+ "sampling_rate": 16000
15
+ },
16
+ "processor_class": "WhisperProcessor"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "language": "uz",
10
+ "local_files_only": false,
11
+ "model_max_length": 1024,
12
+ "pad_token": "<|endoftext|>",
13
+ "predict_timestamps": false,
14
+ "processor_class": "WhisperProcessor",
15
+ "return_attention_mask": false,
16
+ "task": "transcribe",
17
+ "tokenizer_class": "WhisperTokenizer",
18
+ "unk_token": "<|endoftext|>"
19
+ }