vladimirsierra commited on
Commit
32f38a1
1 Parent(s): 9ac4222

End of training

Browse files
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - multilingual
4
+ license: apache-2.0
5
+ base_model: openai/whisper-large
6
+ tags:
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Whisper large spanish finetuned
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Whisper large spanish finetuned
17
+
18
+ This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the Common Voice 11.0 dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 1e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 1
44
+ - training_steps: 3
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.37.1
54
+ - Pytorch 2.1.0+cu121
55
+ - Datasets 2.16.1
56
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-large",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
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": 1280,
17
+ "decoder_attention_heads": 20,
18
+ "decoder_ffn_dim": 5120,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 32,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 20,
24
+ "encoder_ffn_dim": 5120,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 32,
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
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 32,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [
60
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50358,
144
+ 50359,
145
+ 50360,
146
+ 50361,
147
+ 50362
148
+ ],
149
+ "torch_dtype": "float32",
150
+ "transformers_version": "4.37.1",
151
+ "use_cache": true,
152
+ "use_weighted_layer_sum": false,
153
+ "vocab_size": 51865
154
+ }
generation_config.json ADDED
@@ -0,0 +1,260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 9,
5
+ 19
6
+ ],
7
+ [
8
+ 11,
9
+ 2
10
+ ],
11
+ [
12
+ 11,
13
+ 4
14
+ ],
15
+ [
16
+ 11,
17
+ 17
18
+ ],
19
+ [
20
+ 22,
21
+ 7
22
+ ],
23
+ [
24
+ 22,
25
+ 11
26
+ ],
27
+ [
28
+ 22,
29
+ 17
30
+ ],
31
+ [
32
+ 23,
33
+ 2
34
+ ],
35
+ [
36
+ 23,
37
+ 15
38
+ ]
39
+ ],
40
+ "begin_suppress_tokens": [
41
+ 220,
42
+ 50257
43
+ ],
44
+ "bos_token_id": 50257,
45
+ "decoder_start_token_id": 50258,
46
+ "eos_token_id": 50257,
47
+ "forced_decoder_ids": [
48
+ [
49
+ 1,
50
+ null
51
+ ],
52
+ [
53
+ 2,
54
+ 50359
55
+ ]
56
+ ],
57
+ "is_multilingual": true,
58
+ "lang_to_id": {
59
+ "<|af|>": 50327,
60
+ "<|am|>": 50334,
61
+ "<|ar|>": 50272,
62
+ "<|as|>": 50350,
63
+ "<|az|>": 50304,
64
+ "<|ba|>": 50355,
65
+ "<|be|>": 50330,
66
+ "<|bg|>": 50292,
67
+ "<|bn|>": 50302,
68
+ "<|bo|>": 50347,
69
+ "<|br|>": 50309,
70
+ "<|bs|>": 50315,
71
+ "<|ca|>": 50270,
72
+ "<|cs|>": 50283,
73
+ "<|cy|>": 50297,
74
+ "<|da|>": 50285,
75
+ "<|de|>": 50261,
76
+ "<|el|>": 50281,
77
+ "<|en|>": 50259,
78
+ "<|es|>": 50262,
79
+ "<|et|>": 50307,
80
+ "<|eu|>": 50310,
81
+ "<|fa|>": 50300,
82
+ "<|fi|>": 50277,
83
+ "<|fo|>": 50338,
84
+ "<|fr|>": 50265,
85
+ "<|gl|>": 50319,
86
+ "<|gu|>": 50333,
87
+ "<|haw|>": 50352,
88
+ "<|ha|>": 50354,
89
+ "<|he|>": 50279,
90
+ "<|hi|>": 50276,
91
+ "<|hr|>": 50291,
92
+ "<|ht|>": 50339,
93
+ "<|hu|>": 50286,
94
+ "<|hy|>": 50312,
95
+ "<|id|>": 50275,
96
+ "<|is|>": 50311,
97
+ "<|it|>": 50274,
98
+ "<|ja|>": 50266,
99
+ "<|jw|>": 50356,
100
+ "<|ka|>": 50329,
101
+ "<|kk|>": 50316,
102
+ "<|km|>": 50323,
103
+ "<|kn|>": 50306,
104
+ "<|ko|>": 50264,
105
+ "<|la|>": 50294,
106
+ "<|lb|>": 50345,
107
+ "<|ln|>": 50353,
108
+ "<|lo|>": 50336,
109
+ "<|lt|>": 50293,
110
+ "<|lv|>": 50301,
111
+ "<|mg|>": 50349,
112
+ "<|mi|>": 50295,
113
+ "<|mk|>": 50308,
114
+ "<|ml|>": 50296,
115
+ "<|mn|>": 50314,
116
+ "<|mr|>": 50320,
117
+ "<|ms|>": 50282,
118
+ "<|mt|>": 50343,
119
+ "<|my|>": 50346,
120
+ "<|ne|>": 50313,
121
+ "<|nl|>": 50271,
122
+ "<|nn|>": 50342,
123
+ "<|no|>": 50288,
124
+ "<|oc|>": 50328,
125
+ "<|pa|>": 50321,
126
+ "<|pl|>": 50269,
127
+ "<|ps|>": 50340,
128
+ "<|pt|>": 50267,
129
+ "<|ro|>": 50284,
130
+ "<|ru|>": 50263,
131
+ "<|sa|>": 50344,
132
+ "<|sd|>": 50332,
133
+ "<|si|>": 50322,
134
+ "<|sk|>": 50298,
135
+ "<|sl|>": 50305,
136
+ "<|sn|>": 50324,
137
+ "<|so|>": 50326,
138
+ "<|sq|>": 50317,
139
+ "<|sr|>": 50303,
140
+ "<|su|>": 50357,
141
+ "<|sv|>": 50273,
142
+ "<|sw|>": 50318,
143
+ "<|ta|>": 50287,
144
+ "<|te|>": 50299,
145
+ "<|tg|>": 50331,
146
+ "<|th|>": 50289,
147
+ "<|tk|>": 50341,
148
+ "<|tl|>": 50348,
149
+ "<|tr|>": 50268,
150
+ "<|tt|>": 50351,
151
+ "<|uk|>": 50280,
152
+ "<|ur|>": 50290,
153
+ "<|uz|>": 50337,
154
+ "<|vi|>": 50278,
155
+ "<|yi|>": 50335,
156
+ "<|yo|>": 50325,
157
+ "<|zh|>": 50260
158
+ },
159
+ "max_initial_timestamp_index": 50,
160
+ "max_length": 448,
161
+ "no_timestamps_token_id": 50363,
162
+ "pad_token_id": 50257,
163
+ "prev_sot_token_id": 50361,
164
+ "return_timestamps": false,
165
+ "suppress_tokens": [
166
+ 1,
167
+ 2,
168
+ 7,
169
+ 8,
170
+ 9,
171
+ 10,
172
+ 14,
173
+ 25,
174
+ 26,
175
+ 27,
176
+ 28,
177
+ 29,
178
+ 31,
179
+ 58,
180
+ 59,
181
+ 60,
182
+ 61,
183
+ 62,
184
+ 63,
185
+ 90,
186
+ 91,
187
+ 92,
188
+ 93,
189
+ 359,
190
+ 503,
191
+ 522,
192
+ 542,
193
+ 873,
194
+ 893,
195
+ 902,
196
+ 918,
197
+ 922,
198
+ 931,
199
+ 1350,
200
+ 1853,
201
+ 1982,
202
+ 2460,
203
+ 2627,
204
+ 3246,
205
+ 3253,
206
+ 3268,
207
+ 3536,
208
+ 3846,
209
+ 3961,
210
+ 4183,
211
+ 4667,
212
+ 6585,
213
+ 6647,
214
+ 7273,
215
+ 9061,
216
+ 9383,
217
+ 10428,
218
+ 10929,
219
+ 11938,
220
+ 12033,
221
+ 12331,
222
+ 12562,
223
+ 13793,
224
+ 14157,
225
+ 14635,
226
+ 15265,
227
+ 15618,
228
+ 16553,
229
+ 16604,
230
+ 18362,
231
+ 18956,
232
+ 20075,
233
+ 21675,
234
+ 22520,
235
+ 26130,
236
+ 26161,
237
+ 26435,
238
+ 28279,
239
+ 29464,
240
+ 31650,
241
+ 32302,
242
+ 32470,
243
+ 36865,
244
+ 42863,
245
+ 47425,
246
+ 49870,
247
+ 50254,
248
+ 50258,
249
+ 50358,
250
+ 50359,
251
+ 50360,
252
+ 50361,
253
+ 50362
254
+ ],
255
+ "task_to_id": {
256
+ "transcribe": 50359,
257
+ "translate": 50358
258
+ },
259
+ "transformers_version": "4.37.1"
260
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8367f71e5d216a2dec4d825315681c30c471be80bcf94e7701d17e801b0fe5d
3
+ size 4992706480
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764f4e684d3bb3eeb4ea5484922f3213e0c75d75c4bb5f14b7c338f7e6c9a29d
3
+ size 1180663192
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
runs/Jan25_05-14-13_cdf6dc583b47/events.out.tfevents.1706159657.cdf6dc583b47.263.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a052e8937fc4e9a29028322c696423f2e77edeaf38db3c79674c1fa4e6995283
3
+ size 4184
runs/Jan25_05-17-19_cdf6dc583b47/events.out.tfevents.1706159841.cdf6dc583b47.1816.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d439fbd5294d3d5381974f1cdc0193d85b806aed810d741553ebeee58e99471
3
+ size 4184
runs/Jan25_05-20-31_cdf6dc583b47/events.out.tfevents.1706160034.cdf6dc583b47.2756.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c4927dede52f9bd60f9d1e5102d7f957c717bf822eb34d566ac324d1da142c
3
+ size 6496
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2fe788c38559a0465399fee398c806ae6e6450ba9a2ccb2da0ed1bf2f6e6b86
3
+ size 4856