Hugging Face's logo

ctaguchi
/
ssc-led-mms-model-mix-adapt-max3-devtrain

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Community
ctaguchi commited on
Commit
cd87456
·
verified ·
1 Parent(s): 1e5b8c1

End of training

Browse files
Files changed (4) hide show
  1. README.md +27 -74
  2. adapter.led.safetensors +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,5 @@
1
  ---
2
  library_name: transformers
3
- license: cc-by-nc-4.0
4
- base_model: facebook/mms-1b-all
5
  tags:
6
  - generated_from_trainer
7
  metrics:
@@ -16,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # ssc-led-mms-model-mix-adapt-max3-devtrain
18
 
19
- This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.3430
22
- - Cer: 0.0817
23
- - Wer: 0.2273
24
 
25
  ## Model description
26
 
@@ -40,84 +38,39 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 0.0005
43
- - train_batch_size: 8
44
  - eval_batch_size: 6
45
  - seed: 42
46
  - gradient_accumulation_steps: 2
47
- - total_train_batch_size: 16
48
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 100
51
- - num_epochs: 20
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
57
- |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
58
- | 1.3217 | 0.3177 | 200 | 0.8190 | 0.2036 | 0.5730 |
59
- | 0.9037 | 0.6354 | 400 | 0.6230 | 0.1620 | 0.4794 |
60
- | 0.8364 | 0.9531 | 600 | 0.5497 | 0.1443 | 0.4293 |
61
- | 0.7856 | 1.2701 | 800 | 0.5116 | 0.1312 | 0.3744 |
62
- | 0.7729 | 1.5878 | 1000 | 0.4956 | 0.1253 | 0.3625 |
63
- | 0.7392 | 1.9055 | 1200 | 0.4786 | 0.1260 | 0.3685 |
64
- | 0.7264 | 2.2224 | 1400 | 0.4743 | 0.1227 | 0.3474 |
65
- | 0.7086 | 2.5401 | 1600 | 0.4620 | 0.1205 | 0.3509 |
66
- | 0.6929 | 2.8578 | 1800 | 0.4505 | 0.1207 | 0.3592 |
67
- | 0.6707 | 3.1747 | 2000 | 0.4399 | 0.1122 | 0.3195 |
68
- | 0.6528 | 3.4925 | 2200 | 0.4312 | 0.1096 | 0.3146 |
69
- | 0.6715 | 3.8102 | 2400 | 0.4234 | 0.1092 | 0.3122 |
70
- | 0.6 | 4.1271 | 2600 | 0.4084 | 0.1069 | 0.3053 |
71
- | 0.659 | 4.4448 | 2800 | 0.4269 | 0.1049 | 0.2951 |
72
- | 0.6167 | 4.7625 | 3000 | 0.4008 | 0.1050 | 0.3000 |
73
- | 0.6597 | 5.0794 | 3200 | 0.4046 | 0.1065 | 0.3026 |
74
- | 0.6122 | 5.3971 | 3400 | 0.4203 | 0.1088 | 0.3149 |
75
- | 0.6035 | 5.7149 | 3600 | 0.3983 | 0.1040 | 0.2959 |
76
- | 0.5459 | 6.0318 | 3800 | 0.3942 | 0.1019 | 0.2900 |
77
- | 0.5763 | 6.3495 | 4000 | 0.3931 | 0.0998 | 0.2798 |
78
- | 0.602 | 6.6672 | 4200 | 0.3923 | 0.0984 | 0.2763 |
79
- | 0.5837 | 6.9849 | 4400 | 0.3884 | 0.1022 | 0.2902 |
80
- | 0.5685 | 7.3018 | 4600 | 0.3754 | 0.0976 | 0.2762 |
81
- | 0.5641 | 7.6195 | 4800 | 0.3968 | 0.1002 | 0.2907 |
82
- | 0.5754 | 7.9373 | 5000 | 0.4131 | 0.1002 | 0.2850 |
83
- | 0.5622 | 8.2542 | 5200 | 0.4025 | 0.0948 | 0.2664 |
84
- | 0.5524 | 8.5719 | 5400 | 0.3922 | 0.0942 | 0.2617 |
85
- | 0.5268 | 8.8896 | 5600 | 0.3743 | 0.0947 | 0.2658 |
86
- | 0.5433 | 9.2065 | 5800 | 0.3743 | 0.0937 | 0.2639 |
87
- | 0.525 | 9.5242 | 6000 | 0.3669 | 0.0929 | 0.2628 |
88
- | 0.5371 | 9.8419 | 6200 | 0.3831 | 0.0928 | 0.2607 |
89
- | 0.5242 | 10.1589 | 6400 | 0.3698 | 0.0929 | 0.2596 |
90
- | 0.5309 | 10.4766 | 6600 | 0.3763 | 0.0932 | 0.2649 |
91
- | 0.5073 | 10.7943 | 6800 | 0.3478 | 0.0906 | 0.2576 |
92
- | 0.4741 | 11.1112 | 7000 | 0.3568 | 0.0914 | 0.2586 |
93
- | 0.5246 | 11.4289 | 7200 | 0.3563 | 0.0911 | 0.2577 |
94
- | 0.5095 | 11.7466 | 7400 | 0.3409 | 0.0915 | 0.2586 |
95
- | 0.5067 | 12.0635 | 7600 | 0.3818 | 0.0890 | 0.2484 |
96
- | 0.5084 | 12.3813 | 7800 | 0.3722 | 0.0892 | 0.2502 |
97
- | 0.5082 | 12.6990 | 8000 | 0.3630 | 0.0896 | 0.2532 |
98
- | 0.4913 | 13.0159 | 8200 | 0.3511 | 0.0876 | 0.2455 |
99
- | 0.4623 | 13.3336 | 8400 | 0.3401 | 0.0867 | 0.2436 |
100
- | 0.4906 | 13.6513 | 8600 | 0.3678 | 0.0873 | 0.2449 |
101
- | 0.4762 | 13.9690 | 8800 | 0.3438 | 0.0854 | 0.2392 |
102
- | 0.4457 | 14.2859 | 9000 | 0.3740 | 0.0848 | 0.2374 |
103
- | 0.4666 | 14.6037 | 9200 | 0.3571 | 0.0846 | 0.2368 |
104
- | 0.4704 | 14.9214 | 9400 | 0.3420 | 0.0843 | 0.2349 |
105
- | 0.4762 | 15.2383 | 9600 | 0.3405 | 0.0855 | 0.2391 |
106
- | 0.4702 | 15.5560 | 9800 | 0.3530 | 0.0849 | 0.2372 |
107
- | 0.4617 | 15.8737 | 10000 | 0.3263 | 0.0837 | 0.2322 |
108
- | 0.45 | 16.1906 | 10200 | 0.3465 | 0.0837 | 0.2360 |
109
- | 0.4493 | 16.5083 | 10400 | 0.3403 | 0.0836 | 0.2370 |
110
- | 0.467 | 16.8261 | 10600 | 0.3467 | 0.0833 | 0.2315 |
111
- | 0.4444 | 17.1430 | 10800 | 0.3365 | 0.0824 | 0.2300 |
112
- | 0.4462 | 17.4607 | 11000 | 0.3435 | 0.0836 | 0.2351 |
113
- | 0.4474 | 17.7784 | 11200 | 0.3469 | 0.0820 | 0.2302 |
114
- | 0.4536 | 18.0953 | 11400 | 0.3475 | 0.0829 | 0.2314 |
115
- | 0.4301 | 18.4130 | 11600 | 0.3402 | 0.0827 | 0.2312 |
116
- | 0.4264 | 18.7307 | 11800 | 0.3423 | 0.0817 | 0.2250 |
117
- | 0.4141 | 19.0477 | 12000 | 0.3438 | 0.0819 | 0.2296 |
118
- | 0.4302 | 19.3654 | 12200 | 0.3469 | 0.0818 | 0.2273 |
119
- | 0.4332 | 19.6831 | 12400 | 0.3429 | 0.0815 | 0.2274 |
120
- | 0.4639 | 20.0 | 12600 | 0.3430 | 0.0817 | 0.2273 |
121
 
122
 
123
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
 
14
 
15
  # ssc-led-mms-model-mix-adapt-max3-devtrain
16
 
17
+ This model was trained from scratch on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.3148
20
+ - Cer: 0.0905
21
+ - Wer: 0.2510
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0005
41
+ - train_batch_size: 1
42
  - eval_batch_size: 6
43
  - seed: 42
44
  - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 2
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 100
49
+ - num_epochs: 5
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
55
+ |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
56
+ | 0.3221 | 0.2683 | 200 | 0.3254 | 0.0958 | 0.2812 |
57
+ | 0.3633 | 0.5366 | 400 | 0.3317 | 0.0969 | 0.2750 |
58
+ | 0.3513 | 0.8048 | 600 | 0.3423 | 0.0981 | 0.2753 |
59
+ | 0.3447 | 1.0724 | 800 | 0.3362 | 0.0941 | 0.2638 |
60
+ | 0.3403 | 1.3407 | 1000 | 0.3415 | 0.0985 | 0.2782 |
61
+ | 0.3358 | 1.6090 | 1200 | 0.3332 | 0.0954 | 0.2685 |
62
+ | 0.3146 | 1.8773 | 1400 | 0.3357 | 0.0977 | 0.2825 |
63
+ | 0.2648 | 2.1449 | 1600 | 0.3264 | 0.0938 | 0.2657 |
64
+ | 0.2934 | 2.4131 | 1800 | 0.3279 | 0.0953 | 0.2756 |
65
+ | 0.3001 | 2.6814 | 2000 | 0.3242 | 0.0948 | 0.2671 |
66
+ | 0.2749 | 2.9497 | 2200 | 0.3238 | 0.0928 | 0.2613 |
67
+ | 0.2686 | 3.2173 | 2400 | 0.3229 | 0.0925 | 0.2604 |
68
+ | 0.2461 | 3.4856 | 2600 | 0.3239 | 0.0934 | 0.2642 |
69
+ | 0.2485 | 3.7539 | 2800 | 0.3190 | 0.0923 | 0.2587 |
70
+ | 0.2703 | 4.0215 | 3000 | 0.3172 | 0.0909 | 0.2542 |
71
+ | 0.2166 | 4.2897 | 3200 | 0.3192 | 0.0899 | 0.2497 |
72
+ | 0.2312 | 4.5580 | 3400 | 0.3170 | 0.0902 | 0.2504 |
73
+ | 0.2244 | 4.8263 | 3600 | 0.3148 | 0.0905 | 0.2510 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
adapter.led.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65d4d02ca6518abe000d53f4bae51ffef6edba53a6e8ba2525ada2d2ea6a0ab5
3
  size 9321220
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aefa7d455872ec1307b728db6e4e50f5128a623a44688766c2ad860794974965
3
  size 9321220
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:defc93ffbf363af0f7e78fc737881472083981cbef747b2d1b7b903dd6e9fca6
3
  size 3859413572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93427d79be569dfb370ecc766d11d1fc383ca26f91e9f064e51b8e4e6e75f6fc
3
  size 3859413572
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dce7597c88169e88da148115dfe0a2cfb0673b5a6fd3acecde1ffeffcb33cb8
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d44093a22ef630b93d304ee16cae40b1d5b61842a3d79ada32c4af01ac6063b
3
  size 5969