Danieljava commited on
Commit
a9b8b83
·
verified ·
1 Parent(s): 23dde8d

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (3) hide show
  1. processor_config.json +17 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +31 -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": "left",
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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "extra_special_tokens": [
9
+ "<|ann|>",
10
+ "<|efi|>",
11
+ "<|ego|>",
12
+ "<|ibb|>",
13
+ "<|idm|>",
14
+ "<|igl|>",
15
+ "<|ig|>",
16
+ "<|nup|>",
17
+ "<|tiv|>",
18
+ "<|urh|>"
19
+ ],
20
+ "is_local": false,
21
+ "language": "english",
22
+ "model_max_length": 1024,
23
+ "pad_token": "<|endoftext|>",
24
+ "padding_side": "left",
25
+ "predict_timestamps": false,
26
+ "processor_class": "WhisperProcessor",
27
+ "return_attention_mask": false,
28
+ "task": "translate",
29
+ "tokenizer_class": "WhisperTokenizer",
30
+ "unk_token": "<|endoftext|>"
31
+ }