sanchit-gandhi HF staff commited on
Commit
a28062b
1 Parent(s): b364874

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-base",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "WhisperForAudioClassification"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "classifier_proj_size": 256,
15
+ "d_model": 512,
16
+ "decoder_attention_heads": 8,
17
+ "decoder_ffn_dim": 2048,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 6,
20
+ "decoder_start_token_id": 50258,
21
+ "dropout": 0.0,
22
+ "encoder_attention_heads": 8,
23
+ "encoder_ffn_dim": 2048,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 50257,
27
+ "finetuning_task": "audio-classification",
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": "Arabic",
44
+ "1": "Basque",
45
+ "10": "Dutch",
46
+ "11": "English",
47
+ "12": "Esperanto",
48
+ "13": "Estonian",
49
+ "14": "French",
50
+ "15": "Frisian",
51
+ "16": "Georgian",
52
+ "17": "German",
53
+ "18": "Greek",
54
+ "19": "Hakha_Chin",
55
+ "2": "Breton",
56
+ "20": "Indonesian",
57
+ "21": "Interlingua",
58
+ "22": "Italian",
59
+ "23": "Japanese",
60
+ "24": "Kabyle",
61
+ "25": "Kinyarwanda",
62
+ "26": "Kyrgyz",
63
+ "27": "Latvian",
64
+ "28": "Maltese",
65
+ "29": "Mangolian",
66
+ "3": "Catalan",
67
+ "30": "Persian",
68
+ "31": "Polish",
69
+ "32": "Portuguese",
70
+ "33": "Romanian",
71
+ "34": "Romansh_Sursilvan",
72
+ "35": "Russian",
73
+ "36": "Sakha",
74
+ "37": "Slovenian",
75
+ "38": "Spanish",
76
+ "39": "Swedish",
77
+ "4": "Chinese_China",
78
+ "40": "Tamil",
79
+ "41": "Tatar",
80
+ "42": "Turkish",
81
+ "43": "Ukranian",
82
+ "44": "Welsh",
83
+ "5": "Chinese_Hongkong",
84
+ "6": "Chinese_Taiwan",
85
+ "7": "Chuvash",
86
+ "8": "Czech",
87
+ "9": "Dhivehi"
88
+ },
89
+ "init_std": 0.02,
90
+ "is_encoder_decoder": true,
91
+ "label2id": {
92
+ "Arabic": "0",
93
+ "Basque": "1",
94
+ "Breton": "2",
95
+ "Catalan": "3",
96
+ "Chinese_China": "4",
97
+ "Chinese_Hongkong": "5",
98
+ "Chinese_Taiwan": "6",
99
+ "Chuvash": "7",
100
+ "Czech": "8",
101
+ "Dhivehi": "9",
102
+ "Dutch": "10",
103
+ "English": "11",
104
+ "Esperanto": "12",
105
+ "Estonian": "13",
106
+ "French": "14",
107
+ "Frisian": "15",
108
+ "Georgian": "16",
109
+ "German": "17",
110
+ "Greek": "18",
111
+ "Hakha_Chin": "19",
112
+ "Indonesian": "20",
113
+ "Interlingua": "21",
114
+ "Italian": "22",
115
+ "Japanese": "23",
116
+ "Kabyle": "24",
117
+ "Kinyarwanda": "25",
118
+ "Kyrgyz": "26",
119
+ "Latvian": "27",
120
+ "Maltese": "28",
121
+ "Mangolian": "29",
122
+ "Persian": "30",
123
+ "Polish": "31",
124
+ "Portuguese": "32",
125
+ "Romanian": "33",
126
+ "Romansh_Sursilvan": "34",
127
+ "Russian": "35",
128
+ "Sakha": "36",
129
+ "Slovenian": "37",
130
+ "Spanish": "38",
131
+ "Swedish": "39",
132
+ "Tamil": "40",
133
+ "Tatar": "41",
134
+ "Turkish": "42",
135
+ "Ukranian": "43",
136
+ "Welsh": "44"
137
+ },
138
+ "max_length": 448,
139
+ "max_source_positions": 1500,
140
+ "max_target_positions": 448,
141
+ "model_type": "whisper",
142
+ "num_hidden_layers": 6,
143
+ "num_mel_bins": 80,
144
+ "pad_token_id": 50257,
145
+ "scale_embedding": false,
146
+ "suppress_tokens": [
147
+ 1,
148
+ 2,
149
+ 7,
150
+ 8,
151
+ 9,
152
+ 10,
153
+ 14,
154
+ 25,
155
+ 26,
156
+ 27,
157
+ 28,
158
+ 29,
159
+ 31,
160
+ 58,
161
+ 59,
162
+ 60,
163
+ 61,
164
+ 62,
165
+ 63,
166
+ 90,
167
+ 91,
168
+ 92,
169
+ 93,
170
+ 359,
171
+ 503,
172
+ 522,
173
+ 542,
174
+ 873,
175
+ 893,
176
+ 902,
177
+ 918,
178
+ 922,
179
+ 931,
180
+ 1350,
181
+ 1853,
182
+ 1982,
183
+ 2460,
184
+ 2627,
185
+ 3246,
186
+ 3253,
187
+ 3268,
188
+ 3536,
189
+ 3846,
190
+ 3961,
191
+ 4183,
192
+ 4667,
193
+ 6585,
194
+ 6647,
195
+ 7273,
196
+ 9061,
197
+ 9383,
198
+ 10428,
199
+ 10929,
200
+ 11938,
201
+ 12033,
202
+ 12331,
203
+ 12562,
204
+ 13793,
205
+ 14157,
206
+ 14635,
207
+ 15265,
208
+ 15618,
209
+ 16553,
210
+ 16604,
211
+ 18362,
212
+ 18956,
213
+ 20075,
214
+ 21675,
215
+ 22520,
216
+ 26130,
217
+ 26161,
218
+ 26435,
219
+ 28279,
220
+ 29464,
221
+ 31650,
222
+ 32302,
223
+ 32470,
224
+ 36865,
225
+ 42863,
226
+ 47425,
227
+ 49870,
228
+ 50254,
229
+ 50258,
230
+ 50360,
231
+ 50361,
232
+ 50362
233
+ ],
234
+ "torch_dtype": "float32",
235
+ "transformers_version": "4.27.0.dev0",
236
+ "use_cache": true,
237
+ "use_weighted_layer_sum": false,
238
+ "vocab_size": 51865
239
+ }
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98377fc0cfb572568f9a075dc93a0610b9ca1600b9e3236dccc42922b5fa64fa
3
+ size 82966945
runs/Feb24_10-11-38_sanchit-single-v100/1677233514.69767/events.out.tfevents.1677233514.sanchit-single-v100.22712.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd769d74f47e75702f9391ec2592b98da89f4d1b69fc679aee58cb6c00754d3
3
+ size 5847
runs/Feb24_10-11-38_sanchit-single-v100/events.out.tfevents.1677233514.sanchit-single-v100.22712.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1441bc3861b4f4f173cb863f9378c46b7f2aafe87af23aec32bf8c1cb2a1c60
3
+ size 11955
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e288a244c846752947bc16358c40c5b0c9e89f8375ce5d0004ee4bb3b4055aa
3
+ size 3643