bagasshw commited on
Commit
31e0912
·
verified ·
1 Parent(s): 6de6156

Training in progress, step 50001

Browse files
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: openai/whisper-tiny
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: whisper-tiny-javanese-openslr-v5
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # whisper-tiny-javanese-openslr-v5
18
+
19
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2530
22
+ - Wer: 0.1763
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 4
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 16
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - training_steps: 50000
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
57
+ | 1.0859 | 0.4325 | 1000 | 0.9075 | 0.6419 |
58
+ | 0.7132 | 0.8651 | 2000 | 0.6100 | 0.5481 |
59
+ | 0.5258 | 1.2976 | 3000 | 0.4822 | 0.6352 |
60
+ | 0.4521 | 1.7301 | 4000 | 0.4058 | 0.4619 |
61
+ | 0.3848 | 1.0813 | 5000 | 0.4022 | 0.3778 |
62
+ | 0.351 | 1.2976 | 6000 | 0.3711 | 0.3326 |
63
+ | 0.3277 | 1.5138 | 7000 | 0.3546 | 0.3053 |
64
+ | 0.3122 | 1.7301 | 8000 | 0.3370 | 0.2862 |
65
+ | 0.3433 | 1.9464 | 9000 | 0.3173 | 0.2501 |
66
+ | 0.2336 | 2.1626 | 10000 | 0.3144 | 0.2563 |
67
+ | 0.2238 | 2.3789 | 11000 | 0.3043 | 0.2355 |
68
+ | 0.2225 | 2.5952 | 12000 | 0.2969 | 0.2403 |
69
+ | 0.218 | 2.8114 | 13000 | 0.2881 | 0.2326 |
70
+ | 0.1778 | 3.0277 | 14000 | 0.2848 | 0.2142 |
71
+ | 0.1669 | 3.2439 | 15000 | 0.2824 | 0.2114 |
72
+ | 0.1621 | 3.4602 | 16000 | 0.2812 | 0.2131 |
73
+ | 0.1585 | 3.6765 | 17000 | 0.2753 | 0.2114 |
74
+ | 0.1567 | 3.8927 | 18000 | 0.2723 | 0.1973 |
75
+ | 0.1092 | 4.1090 | 19000 | 0.2706 | 0.2005 |
76
+ | 0.1122 | 4.3253 | 20000 | 0.2704 | 0.2092 |
77
+ | 0.1138 | 4.5415 | 21000 | 0.2706 | 0.1959 |
78
+ | 0.121 | 4.7578 | 22000 | 0.2650 | 0.1952 |
79
+ | 0.11 | 4.9740 | 23000 | 0.2642 | 0.1935 |
80
+ | 0.0848 | 5.1903 | 24000 | 0.2655 | 0.1916 |
81
+ | 0.0844 | 5.4066 | 25000 | 0.2644 | 0.1890 |
82
+ | 0.0836 | 5.6228 | 26000 | 0.2626 | 0.1905 |
83
+ | 0.087 | 5.8391 | 27000 | 0.2587 | 0.1885 |
84
+ | 0.059 | 6.0554 | 28000 | 0.2594 | 0.1827 |
85
+ | 0.0596 | 6.2716 | 29000 | 0.2606 | 0.1835 |
86
+ | 0.0616 | 6.4879 | 30000 | 0.2587 | 0.1895 |
87
+ | 0.0634 | 6.7042 | 31000 | 0.2577 | 0.1805 |
88
+ | 0.0647 | 6.9204 | 32000 | 0.2557 | 0.1859 |
89
+ | 0.0467 | 7.1367 | 33000 | 0.2584 | 0.1800 |
90
+ | 0.0474 | 7.3529 | 34000 | 0.2545 | 0.1800 |
91
+ | 0.0478 | 7.5692 | 35000 | 0.2588 | 0.1827 |
92
+ | 0.0485 | 7.7855 | 36000 | 0.2559 | 0.1800 |
93
+ | 0.0456 | 8.0017 | 37000 | 0.2556 | 0.1804 |
94
+ | 0.0361 | 8.2180 | 38000 | 0.2560 | 0.1844 |
95
+ | 0.0354 | 8.4343 | 39000 | 0.2550 | 0.1806 |
96
+ | 0.0365 | 8.6505 | 40000 | 0.2557 | 0.1873 |
97
+ | 0.0388 | 8.8668 | 41000 | 0.2540 | 0.1843 |
98
+ | 0.0317 | 9.0830 | 42000 | 0.2547 | 0.1819 |
99
+ | 0.0334 | 9.2993 | 43000 | 0.2556 | 0.1780 |
100
+ | 0.033 | 9.5156 | 44000 | 0.2552 | 0.1801 |
101
+ | 0.0313 | 9.7318 | 45000 | 0.2540 | 0.1787 |
102
+ | 0.0318 | 9.9481 | 46000 | 0.2537 | 0.1772 |
103
+ | 0.0285 | 10.1644 | 47000 | 0.2534 | 0.1764 |
104
+ | 0.0256 | 10.3806 | 48000 | 0.2530 | 0.1771 |
105
+ | 0.0288 | 10.5969 | 49000 | 0.2532 | 0.1760 |
106
+ | 0.0265 | 10.8131 | 50000 | 0.2530 | 0.1763 |
107
+
108
+
109
+ ### Framework versions
110
+
111
+ - Transformers 4.50.0.dev0
112
+ - Pytorch 2.6.0+cu126
113
+ - Datasets 2.16.0
114
+ - Tokenizers 0.21.1
generation_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "begin_suppress_tokens": [
29
+ 220,
30
+ 50257
31
+ ],
32
+ "bos_token_id": 50257,
33
+ "decoder_start_token_id": 50258,
34
+ "eos_token_id": 50257,
35
+ "is_multilingual": true,
36
+ "lang_to_id": {
37
+ "<|af|>": 50327,
38
+ "<|am|>": 50334,
39
+ "<|ar|>": 50272,
40
+ "<|as|>": 50350,
41
+ "<|az|>": 50304,
42
+ "<|ba|>": 50355,
43
+ "<|be|>": 50330,
44
+ "<|bg|>": 50292,
45
+ "<|bn|>": 50302,
46
+ "<|bo|>": 50347,
47
+ "<|br|>": 50309,
48
+ "<|bs|>": 50315,
49
+ "<|ca|>": 50270,
50
+ "<|cs|>": 50283,
51
+ "<|cy|>": 50297,
52
+ "<|da|>": 50285,
53
+ "<|de|>": 50261,
54
+ "<|el|>": 50281,
55
+ "<|en|>": 50259,
56
+ "<|es|>": 50262,
57
+ "<|et|>": 50307,
58
+ "<|eu|>": 50310,
59
+ "<|fa|>": 50300,
60
+ "<|fi|>": 50277,
61
+ "<|fo|>": 50338,
62
+ "<|fr|>": 50265,
63
+ "<|gl|>": 50319,
64
+ "<|gu|>": 50333,
65
+ "<|haw|>": 50352,
66
+ "<|ha|>": 50354,
67
+ "<|he|>": 50279,
68
+ "<|hi|>": 50276,
69
+ "<|hr|>": 50291,
70
+ "<|ht|>": 50339,
71
+ "<|hu|>": 50286,
72
+ "<|hy|>": 50312,
73
+ "<|id|>": 50275,
74
+ "<|is|>": 50311,
75
+ "<|it|>": 50274,
76
+ "<|ja|>": 50266,
77
+ "<|jw|>": 50356,
78
+ "<|ka|>": 50329,
79
+ "<|kk|>": 50316,
80
+ "<|km|>": 50323,
81
+ "<|kn|>": 50306,
82
+ "<|ko|>": 50264,
83
+ "<|la|>": 50294,
84
+ "<|lb|>": 50345,
85
+ "<|ln|>": 50353,
86
+ "<|lo|>": 50336,
87
+ "<|lt|>": 50293,
88
+ "<|lv|>": 50301,
89
+ "<|mg|>": 50349,
90
+ "<|mi|>": 50295,
91
+ "<|mk|>": 50308,
92
+ "<|ml|>": 50296,
93
+ "<|mn|>": 50314,
94
+ "<|mr|>": 50320,
95
+ "<|ms|>": 50282,
96
+ "<|mt|>": 50343,
97
+ "<|my|>": 50346,
98
+ "<|ne|>": 50313,
99
+ "<|nl|>": 50271,
100
+ "<|nn|>": 50342,
101
+ "<|no|>": 50288,
102
+ "<|oc|>": 50328,
103
+ "<|pa|>": 50321,
104
+ "<|pl|>": 50269,
105
+ "<|ps|>": 50340,
106
+ "<|pt|>": 50267,
107
+ "<|ro|>": 50284,
108
+ "<|ru|>": 50263,
109
+ "<|sa|>": 50344,
110
+ "<|sd|>": 50332,
111
+ "<|si|>": 50322,
112
+ "<|sk|>": 50298,
113
+ "<|sl|>": 50305,
114
+ "<|sn|>": 50324,
115
+ "<|so|>": 50326,
116
+ "<|sq|>": 50317,
117
+ "<|sr|>": 50303,
118
+ "<|su|>": 50357,
119
+ "<|sv|>": 50273,
120
+ "<|sw|>": 50318,
121
+ "<|ta|>": 50287,
122
+ "<|te|>": 50299,
123
+ "<|tg|>": 50331,
124
+ "<|th|>": 50289,
125
+ "<|tk|>": 50341,
126
+ "<|tl|>": 50348,
127
+ "<|tr|>": 50268,
128
+ "<|tt|>": 50351,
129
+ "<|uk|>": 50280,
130
+ "<|ur|>": 50290,
131
+ "<|uz|>": 50337,
132
+ "<|vi|>": 50278,
133
+ "<|yi|>": 50335,
134
+ "<|yo|>": 50325,
135
+ "<|zh|>": 50260
136
+ },
137
+ "language": null,
138
+ "max_initial_timestamp_index": 50,
139
+ "max_length": 448,
140
+ "no_timestamps_token_id": 50363,
141
+ "pad_token_id": 50257,
142
+ "prev_sot_token_id": 50361,
143
+ "return_timestamps": false,
144
+ "suppress_tokens": [
145
+ 1,
146
+ 2,
147
+ 7,
148
+ 8,
149
+ 9,
150
+ 10,
151
+ 14,
152
+ 25,
153
+ 26,
154
+ 27,
155
+ 28,
156
+ 29,
157
+ 31,
158
+ 58,
159
+ 59,
160
+ 60,
161
+ 61,
162
+ 62,
163
+ 63,
164
+ 90,
165
+ 91,
166
+ 92,
167
+ 93,
168
+ 359,
169
+ 503,
170
+ 522,
171
+ 542,
172
+ 873,
173
+ 893,
174
+ 902,
175
+ 918,
176
+ 922,
177
+ 931,
178
+ 1350,
179
+ 1853,
180
+ 1982,
181
+ 2460,
182
+ 2627,
183
+ 3246,
184
+ 3253,
185
+ 3268,
186
+ 3536,
187
+ 3846,
188
+ 3961,
189
+ 4183,
190
+ 4667,
191
+ 6585,
192
+ 6647,
193
+ 7273,
194
+ 9061,
195
+ 9383,
196
+ 10428,
197
+ 10929,
198
+ 11938,
199
+ 12033,
200
+ 12331,
201
+ 12562,
202
+ 13793,
203
+ 14157,
204
+ 14635,
205
+ 15265,
206
+ 15618,
207
+ 16553,
208
+ 16604,
209
+ 18362,
210
+ 18956,
211
+ 20075,
212
+ 21675,
213
+ 22520,
214
+ 26130,
215
+ 26161,
216
+ 26435,
217
+ 28279,
218
+ 29464,
219
+ 31650,
220
+ 32302,
221
+ 32470,
222
+ 36865,
223
+ 42863,
224
+ 47425,
225
+ 49870,
226
+ 50254,
227
+ 50258,
228
+ 50358,
229
+ 50359,
230
+ 50360,
231
+ 50361,
232
+ 50362
233
+ ],
234
+ "task": "transcribe",
235
+ "task_to_id": {
236
+ "transcribe": 50359,
237
+ "translate": 50358
238
+ },
239
+ "transformers_version": "4.50.0.dev0"
240
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e04c20f28a2e1b4721f93018410145e82d874ac27e4be4f8ae623450112f7df
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c4c5980d1ab51a933508a406e33a6aa6f4e24a6a87e246759c920e14b067216
3
  size 151061672
runs/Apr05_20-40-41_dgx-a100/events.out.tfevents.1743860638.dgx-a100.674192.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b00214e2b4fdfab0395d837e0809472dd0749984efc56442e09ff391b8dc4db8
3
- size 57156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b919a740dfd1521a9631cc45452686d34952db177cfd0e0a3153e2bae76dec84
3
+ size 57586
runs/Apr05_21-26-10_dgx-a100/events.out.tfevents.1743863385.dgx-a100.722765.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4892eb140a250dc453e3d98d097662aa4d08735f148b8624dd479863bf0778a2
3
- size 56402
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d179cd64e4e3ef54bcde1a1cc472a15e78cba670f374808af1d9bc51fb97d30
3
+ size 56832
runs/Apr06_18-48-31_dgx-a100/events.out.tfevents.1743940333.dgx-a100.2071240.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e633e338b042b74a21095e847a6d1f397b99143349f2206b4ce58565a4a70ed7
3
- size 29981
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c93026d987fcdd54d1b4483a3ccc962edafa036ccd800e705a64198bb87431c0
3
+ size 30411
runs/Apr07_06-00-57_dgx-a100/events.out.tfevents.1743980688.dgx-a100.2782658.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f57b2afe5660a84f62612d92f48c5b36b00a49f56204e8b97a3723d2523a8966
3
- size 16960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46d464f6aedcae98ee88521e665641424dc74e28f148aea9ba74977b537b425
3
+ size 17390
runs/Apr07_18-09-34_dgx-a100/events.out.tfevents.1744024387.dgx-a100.3614384.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f900bd1dd7d3a6840682ab0ae91d29d1b0f6f7a6cf5539bcbed97c797ee723
3
+ size 12908
runs/Apr08_09-20-26_dgx-a100/events.out.tfevents.1744079092.dgx-a100.554420.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4dd84fb3b000fec5df5701f9dbbec962d58b62bc5156e362f94755de42005fa
3
+ size 7312
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c1372f631cdda74319d84ef0f00af099630f2f7bc4087b9ea502c2941f499fe
3
  size 5688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:712b0ee738eff4d66e38f50dd9a237487e74ad1d3d25c6bd3e79966fd634121c
3
  size 5688