moonseok commited on
Commit
8174658
1 Parent(s): 47a5e0a

Training in progress, epoch 0

Browse files
Files changed (4) hide show
  1. config.json +228 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +14 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,228 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForAudioClassification"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "id2label": {
43
+ "0": 0,
44
+ "1": 1,
45
+ "10": 10,
46
+ "11": 11,
47
+ "12": 12,
48
+ "13": 13,
49
+ "14": 14,
50
+ "15": 15,
51
+ "16": 16,
52
+ "17": 17,
53
+ "18": 18,
54
+ "19": 19,
55
+ "2": 2,
56
+ "20": 20,
57
+ "21": 21,
58
+ "22": 22,
59
+ "23": 23,
60
+ "24": 24,
61
+ "25": 25,
62
+ "26": 26,
63
+ "27": 27,
64
+ "28": 28,
65
+ "29": 29,
66
+ "3": 3,
67
+ "30": 30,
68
+ "31": 31,
69
+ "32": 32,
70
+ "33": 33,
71
+ "34": 34,
72
+ "35": 35,
73
+ "4": 4,
74
+ "5": 5,
75
+ "6": 6,
76
+ "7": 7,
77
+ "8": 8,
78
+ "9": 9
79
+ },
80
+ "init_std": 0.02,
81
+ "is_encoder_decoder": true,
82
+ "label2id": {
83
+ "0": 0,
84
+ "1": 1,
85
+ "10": 10,
86
+ "11": 11,
87
+ "12": 12,
88
+ "13": 13,
89
+ "14": 14,
90
+ "15": 15,
91
+ "16": 16,
92
+ "17": 17,
93
+ "18": 18,
94
+ "19": 19,
95
+ "2": 2,
96
+ "20": 20,
97
+ "21": 21,
98
+ "22": 22,
99
+ "23": 23,
100
+ "24": 24,
101
+ "25": 25,
102
+ "26": 26,
103
+ "27": 27,
104
+ "28": 28,
105
+ "29": 29,
106
+ "3": 3,
107
+ "30": 30,
108
+ "31": 31,
109
+ "32": 32,
110
+ "33": 33,
111
+ "34": 34,
112
+ "35": 35,
113
+ "4": 4,
114
+ "5": 5,
115
+ "6": 6,
116
+ "7": 7,
117
+ "8": 8,
118
+ "9": 9
119
+ },
120
+ "mask_feature_length": 10,
121
+ "mask_feature_min_masks": 0,
122
+ "mask_feature_prob": 0.0,
123
+ "mask_time_length": 10,
124
+ "mask_time_min_masks": 2,
125
+ "mask_time_prob": 0.05,
126
+ "max_length": 448,
127
+ "max_source_positions": 1500,
128
+ "max_target_positions": 448,
129
+ "median_filter_width": 7,
130
+ "model_type": "whisper",
131
+ "num_hidden_layers": 12,
132
+ "num_mel_bins": 80,
133
+ "pad_token_id": 50257,
134
+ "scale_embedding": false,
135
+ "suppress_tokens": [
136
+ 1,
137
+ 2,
138
+ 7,
139
+ 8,
140
+ 9,
141
+ 10,
142
+ 14,
143
+ 25,
144
+ 26,
145
+ 27,
146
+ 28,
147
+ 29,
148
+ 31,
149
+ 58,
150
+ 59,
151
+ 60,
152
+ 61,
153
+ 62,
154
+ 63,
155
+ 90,
156
+ 91,
157
+ 92,
158
+ 93,
159
+ 359,
160
+ 503,
161
+ 522,
162
+ 542,
163
+ 873,
164
+ 893,
165
+ 902,
166
+ 918,
167
+ 922,
168
+ 931,
169
+ 1350,
170
+ 1853,
171
+ 1982,
172
+ 2460,
173
+ 2627,
174
+ 3246,
175
+ 3253,
176
+ 3268,
177
+ 3536,
178
+ 3846,
179
+ 3961,
180
+ 4183,
181
+ 4667,
182
+ 6585,
183
+ 6647,
184
+ 7273,
185
+ 9061,
186
+ 9383,
187
+ 10428,
188
+ 10929,
189
+ 11938,
190
+ 12033,
191
+ 12331,
192
+ 12562,
193
+ 13793,
194
+ 14157,
195
+ 14635,
196
+ 15265,
197
+ 15618,
198
+ 16553,
199
+ 16604,
200
+ 18362,
201
+ 18956,
202
+ 20075,
203
+ 21675,
204
+ 22520,
205
+ 26130,
206
+ 26161,
207
+ 26435,
208
+ 28279,
209
+ 29464,
210
+ 31650,
211
+ 32302,
212
+ 32470,
213
+ 36865,
214
+ 42863,
215
+ 47425,
216
+ 49870,
217
+ 50254,
218
+ 50258,
219
+ 50360,
220
+ 50361,
221
+ 50362
222
+ ],
223
+ "torch_dtype": "float32",
224
+ "transformers_version": "4.35.0",
225
+ "use_cache": true,
226
+ "use_weighted_layer_sum": false,
227
+ "vocab_size": 51865
228
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71fd070fdecee9f7ebe4f288321b80cf9b7949b6c1afff707b9c5671fa80a7d5
3
+ size 353461320
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30965692ceda966776fd3de0098f3e92ef8ec005d91880c8842ee8a4ddd1df1a
3
+ size 4600