Hugging Face's logo

chrislife
/
whisper-tiny

Automatic Speech Recognition
Transformers.js
ONNX
whisper
Model card Files
xet
Community
chrislife commited on
Commit
7f0936d
·
verified ·
1 Parent(s): 9c3e6ea

Upload 13 files

Browse files
Files changed (8) hide show
  1. README.md +2 -2
  2. preprocessor_config.json +14 -0
  3. quant_config.json +115 -0
  4. quantize_config.json +115 -0
  5. special_tokens_map.json +139 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +0 -0
  8. vocab.json +0 -0
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
- base_model: whalesos/whisper-tiny
3
  library_name: transformers.js
4
  ---
5
 
6
- https://huggingface.co/chrislife/whisper-tiny with ONNX weights to be compatible with Transformers.js.
7
 
8
  Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
 
1
  ---
2
+ base_model: openai/whisper-tiny
3
  library_name: transformers.js
4
  ---
5
 
6
+ https://huggingface.co/openai/whisper-tiny with ONNX weights to be compatible with Transformers.js.
7
 
8
  Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
quant_config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Div",
8
+ "Concat",
9
+ "Gather",
10
+ "Less",
11
+ "ReduceMean",
12
+ "MatMul",
13
+ "Erf",
14
+ "Add",
15
+ "Expand",
16
+ "Sub",
17
+ "ConstantOfShape",
18
+ "Range",
19
+ "Sqrt",
20
+ "Slice",
21
+ "Squeeze",
22
+ "Cast",
23
+ "Equal",
24
+ "Where",
25
+ "Constant",
26
+ "Pow",
27
+ "Softmax",
28
+ "Shape",
29
+ "Reshape",
30
+ "Mul",
31
+ "Transpose",
32
+ "Unsqueeze"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "decoder_model_merged": {
37
+ "op_types": [
38
+ "Div",
39
+ "Gather",
40
+ "Concat",
41
+ "Less",
42
+ "ReduceMean",
43
+ "MatMul",
44
+ "Erf",
45
+ "Add",
46
+ "Expand",
47
+ "Sub",
48
+ "ConstantOfShape",
49
+ "Range",
50
+ "Sqrt",
51
+ "Slice",
52
+ "Squeeze",
53
+ "Cast",
54
+ "Equal",
55
+ "Where",
56
+ "If",
57
+ "Constant",
58
+ "Pow",
59
+ "Softmax",
60
+ "Shape",
61
+ "Reshape",
62
+ "Mul",
63
+ "Transpose",
64
+ "Unsqueeze"
65
+ ],
66
+ "weight_type": "QInt8"
67
+ },
68
+ "decoder_with_past_model": {
69
+ "op_types": [
70
+ "Div",
71
+ "Concat",
72
+ "Gather",
73
+ "Constant",
74
+ "Pow",
75
+ "Sub",
76
+ "Mul",
77
+ "Transpose",
78
+ "Add",
79
+ "MatMul",
80
+ "Softmax",
81
+ "Sqrt",
82
+ "Slice",
83
+ "Shape",
84
+ "Reshape",
85
+ "ReduceMean",
86
+ "Erf",
87
+ "Unsqueeze"
88
+ ],
89
+ "weight_type": "QInt8"
90
+ },
91
+ "encoder_model": {
92
+ "op_types": [
93
+ "Div",
94
+ "Gather",
95
+ "Concat",
96
+ "Constant",
97
+ "Pow",
98
+ "Sub",
99
+ "Unsqueeze",
100
+ "Mul",
101
+ "Conv",
102
+ "Transpose",
103
+ "MatMul",
104
+ "Softmax",
105
+ "Sqrt",
106
+ "Shape",
107
+ "Reshape",
108
+ "ReduceMean",
109
+ "Erf",
110
+ "Add"
111
+ ],
112
+ "weight_type": "QUInt8"
113
+ }
114
+ }
115
+ }
quantize_config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Cast",
8
+ "ConstantOfShape",
9
+ "Squeeze",
10
+ "Add",
11
+ "Sub",
12
+ "Equal",
13
+ "Softmax",
14
+ "Where",
15
+ "Less",
16
+ "Concat",
17
+ "Gather",
18
+ "Pow",
19
+ "MatMul",
20
+ "Div",
21
+ "Unsqueeze",
22
+ "Shape",
23
+ "ReduceMean",
24
+ "Transpose",
25
+ "Expand",
26
+ "Constant",
27
+ "Reshape",
28
+ "Sqrt",
29
+ "Slice",
30
+ "Erf",
31
+ "Mul",
32
+ "Range"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "decoder_model_merged": {
37
+ "op_types": [
38
+ "Cast",
39
+ "ConstantOfShape",
40
+ "Squeeze",
41
+ "Add",
42
+ "Sub",
43
+ "Equal",
44
+ "Softmax",
45
+ "Where",
46
+ "Less",
47
+ "Concat",
48
+ "Gather",
49
+ "Pow",
50
+ "MatMul",
51
+ "If",
52
+ "Div",
53
+ "Unsqueeze",
54
+ "Shape",
55
+ "ReduceMean",
56
+ "Transpose",
57
+ "Expand",
58
+ "Constant",
59
+ "Reshape",
60
+ "Sqrt",
61
+ "Slice",
62
+ "Erf",
63
+ "Mul",
64
+ "Range"
65
+ ],
66
+ "weight_type": "QInt8"
67
+ },
68
+ "decoder_with_past_model": {
69
+ "op_types": [
70
+ "Sub",
71
+ "Div",
72
+ "Unsqueeze",
73
+ "Gather",
74
+ "ReduceMean",
75
+ "Pow",
76
+ "Transpose",
77
+ "Softmax",
78
+ "Constant",
79
+ "Reshape",
80
+ "Sqrt",
81
+ "Slice",
82
+ "Erf",
83
+ "MatMul",
84
+ "Concat",
85
+ "Mul",
86
+ "Add",
87
+ "Shape"
88
+ ],
89
+ "weight_type": "QInt8"
90
+ },
91
+ "encoder_model": {
92
+ "op_types": [
93
+ "Div",
94
+ "Sub",
95
+ "Unsqueeze",
96
+ "ReduceMean",
97
+ "Pow",
98
+ "Transpose",
99
+ "Gather",
100
+ "Softmax",
101
+ "Conv",
102
+ "Constant",
103
+ "Reshape",
104
+ "Sqrt",
105
+ "Erf",
106
+ "MatMul",
107
+ "Concat",
108
+ "Mul",
109
+ "Add",
110
+ "Shape"
111
+ ],
112
+ "weight_type": "QUInt8"
113
+ }
114
+ }
115
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|startoftranscript|>",
5
+ "<|en|>",
6
+ "<|zh|>",
7
+ "<|de|>",
8
+ "<|es|>",
9
+ "<|ru|>",
10
+ "<|ko|>",
11
+ "<|fr|>",
12
+ "<|ja|>",
13
+ "<|pt|>",
14
+ "<|tr|>",
15
+ "<|pl|>",
16
+ "<|ca|>",
17
+ "<|nl|>",
18
+ "<|ar|>",
19
+ "<|sv|>",
20
+ "<|it|>",
21
+ "<|id|>",
22
+ "<|hi|>",
23
+ "<|fi|>",
24
+ "<|vi|>",
25
+ "<|he|>",
26
+ "<|uk|>",
27
+ "<|el|>",
28
+ "<|ms|>",
29
+ "<|cs|>",
30
+ "<|ro|>",
31
+ "<|da|>",
32
+ "<|hu|>",
33
+ "<|ta|>",
34
+ "<|no|>",
35
+ "<|th|>",
36
+ "<|ur|>",
37
+ "<|hr|>",
38
+ "<|bg|>",
39
+ "<|lt|>",
40
+ "<|la|>",
41
+ "<|mi|>",
42
+ "<|ml|>",
43
+ "<|cy|>",
44
+ "<|sk|>",
45
+ "<|te|>",
46
+ "<|fa|>",
47
+ "<|lv|>",
48
+ "<|bn|>",
49
+ "<|sr|>",
50
+ "<|az|>",
51
+ "<|sl|>",
52
+ "<|kn|>",
53
+ "<|et|>",
54
+ "<|mk|>",
55
+ "<|br|>",
56
+ "<|eu|>",
57
+ "<|is|>",
58
+ "<|hy|>",
59
+ "<|ne|>",
60
+ "<|mn|>",
61
+ "<|bs|>",
62
+ "<|kk|>",
63
+ "<|sq|>",
64
+ "<|sw|>",
65
+ "<|gl|>",
66
+ "<|mr|>",
67
+ "<|pa|>",
68
+ "<|si|>",
69
+ "<|km|>",
70
+ "<|sn|>",
71
+ "<|yo|>",
72
+ "<|so|>",
73
+ "<|af|>",
74
+ "<|oc|>",
75
+ "<|ka|>",
76
+ "<|be|>",
77
+ "<|tg|>",
78
+ "<|sd|>",
79
+ "<|gu|>",
80
+ "<|am|>",
81
+ "<|yi|>",
82
+ "<|lo|>",
83
+ "<|uz|>",
84
+ "<|fo|>",
85
+ "<|ht|>",
86
+ "<|ps|>",
87
+ "<|tk|>",
88
+ "<|nn|>",
89
+ "<|mt|>",
90
+ "<|sa|>",
91
+ "<|lb|>",
92
+ "<|my|>",
93
+ "<|bo|>",
94
+ "<|tl|>",
95
+ "<|mg|>",
96
+ "<|as|>",
97
+ "<|tt|>",
98
+ "<|haw|>",
99
+ "<|ln|>",
100
+ "<|ha|>",
101
+ "<|ba|>",
102
+ "<|jw|>",
103
+ "<|su|>",
104
+ "<|translate|>",
105
+ "<|transcribe|>",
106
+ "<|startoflm|>",
107
+ "<|startofprev|>",
108
+ "<|nocaptions|>",
109
+ "<|notimestamps|>"
110
+ ],
111
+ "bos_token": {
112
+ "content": "<|endoftext|>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "eos_token": {
119
+ "content": "<|endoftext|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": {
126
+ "content": "<|endoftext|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ },
132
+ "unk_token": {
133
+ "content": "<|endoftext|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ }
139
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff