Hugging Face's logo

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

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Community
ctaguchi commited on
Commit
d9400a4
·
verified ·
1 Parent(s): 110d546

End of training

Browse files
Files changed (4) hide show
  1. README.md +29 -80
  2. adapter.bxk.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-bxk-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: 0.4177
22
- - Cer: 0.1145
23
- - Wer: 0.4635
24
 
25
  ## Model description
26
 
@@ -40,90 +38,41 @@ 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
- | 1.0152 | 0.2880 | 200 | 0.7453 | 0.1792 | 0.6636 |
59
- | 0.9038 | 0.5760 | 400 | 0.6654 | 0.1642 | 0.6124 |
60
- | 0.8634 | 0.8639 | 600 | 0.6451 | 0.1573 | 0.5944 |
61
- | 0.8008 | 1.1512 | 800 | 0.6181 | 0.1539 | 0.5788 |
62
- | 0.8145 | 1.4392 | 1000 | 0.5989 | 0.1500 | 0.5696 |
63
- | 0.7969 | 1.7271 | 1200 | 0.5997 | 0.1508 | 0.5660 |
64
- | 0.7078 | 2.0144 | 1400 | 0.5896 | 0.1481 | 0.5644 |
65
- | 0.7844 | 2.3024 | 1600 | 0.5802 | 0.1484 | 0.5630 |
66
- | 0.7457 | 2.5904 | 1800 | 0.5771 | 0.1442 | 0.5489 |
67
- | 0.7882 | 2.8783 | 2000 | 0.5700 | 0.1432 | 0.5473 |
68
- | 0.7065 | 3.1656 | 2200 | 0.5637 | 0.1423 | 0.5444 |
69
- | 0.7029 | 3.4536 | 2400 | 0.5553 | 0.1409 | 0.5411 |
70
- | 0.7347 | 3.7415 | 2600 | 0.5652 | 0.1406 | 0.5324 |
71
- | 0.7281 | 4.0288 | 2800 | 0.5459 | 0.1398 | 0.5379 |
72
- | 0.7065 | 4.3168 | 3000 | 0.5478 | 0.1418 | 0.5434 |
73
- | 0.6996 | 4.6048 | 3200 | 0.5494 | 0.1387 | 0.5354 |
74
- | 0.7333 | 4.8927 | 3400 | 0.5412 | 0.1391 | 0.5363 |
75
- | 0.6437 | 5.1800 | 3600 | 0.5324 | 0.1379 | 0.5221 |
76
- | 0.7171 | 5.4680 | 3800 | 0.5292 | 0.1361 | 0.5182 |
77
- | 0.7055 | 5.7559 | 4000 | 0.5265 | 0.1365 | 0.5218 |
78
- | 0.6608 | 6.0432 | 4200 | 0.5306 | 0.1358 | 0.5214 |
79
- | 0.6704 | 6.3312 | 4400 | 0.5358 | 0.1351 | 0.5189 |
80
- | 0.6623 | 6.6192 | 4600 | 0.5188 | 0.1359 | 0.5198 |
81
- | 0.689 | 6.9071 | 4800 | 0.5230 | 0.1361 | 0.5225 |
82
- | 0.668 | 7.1944 | 5000 | 0.5113 | 0.1325 | 0.5119 |
83
- | 0.6516 | 7.4824 | 5200 | 0.5126 | 0.1329 | 0.5108 |
84
- | 0.6597 | 7.7703 | 5400 | 0.5140 | 0.1315 | 0.5097 |
85
- | 0.6099 | 8.0576 | 5600 | 0.5126 | 0.1317 | 0.5057 |
86
- | 0.6827 | 8.3456 | 5800 | 0.5238 | 0.1308 | 0.5030 |
87
- | 0.6976 | 8.6335 | 6000 | 0.5031 | 0.1300 | 0.5078 |
88
- | 0.6143 | 8.9215 | 6200 | 0.4909 | 0.1322 | 0.5124 |
89
- | 0.6143 | 9.2088 | 6400 | 0.5019 | 0.1304 | 0.5110 |
90
- | 0.6136 | 9.4968 | 6600 | 0.5229 | 0.1290 | 0.4968 |
91
- | 0.6299 | 9.7847 | 6800 | 0.5080 | 0.1303 | 0.5021 |
92
- | 0.6343 | 10.0720 | 7000 | 0.4889 | 0.1309 | 0.5062 |
93
- | 0.6035 | 10.3600 | 7200 | 0.4830 | 0.1302 | 0.5087 |
94
- | 0.656 | 10.6479 | 7400 | 0.4803 | 0.1276 | 0.4936 |
95
- | 0.6167 | 10.9359 | 7600 | 0.4875 | 0.1271 | 0.4926 |
96
- | 0.6162 | 11.2232 | 7800 | 0.4712 | 0.1262 | 0.4890 |
97
- | 0.5932 | 11.5112 | 8000 | 0.4712 | 0.1261 | 0.4913 |
98
- | 0.6125 | 11.7991 | 8200 | 0.4654 | 0.1274 | 0.5007 |
99
- | 0.5689 | 12.0864 | 8400 | 0.4684 | 0.1247 | 0.4851 |
100
- | 0.5888 | 12.3744 | 8600 | 0.4635 | 0.1242 | 0.4816 |
101
- | 0.61 | 12.6623 | 8800 | 0.4563 | 0.1236 | 0.4828 |
102
- | 0.588 | 12.9503 | 9000 | 0.4517 | 0.1234 | 0.4857 |
103
- | 0.6083 | 13.2376 | 9200 | 0.4457 | 0.1228 | 0.4873 |
104
- | 0.5668 | 13.5256 | 9400 | 0.4483 | 0.1214 | 0.4784 |
105
- | 0.5896 | 13.8135 | 9600 | 0.4472 | 0.1209 | 0.4759 |
106
- | 0.5564 | 14.1008 | 9800 | 0.4411 | 0.1222 | 0.4819 |
107
- | 0.5921 | 14.3888 | 10000 | 0.4425 | 0.1205 | 0.4772 |
108
- | 0.6036 | 14.6767 | 10200 | 0.4410 | 0.1200 | 0.4756 |
109
- | 0.5923 | 14.9647 | 10400 | 0.4349 | 0.1198 | 0.4724 |
110
- | 0.5603 | 15.2520 | 10600 | 0.4357 | 0.1184 | 0.4694 |
111
- | 0.5548 | 15.5400 | 10800 | 0.4362 | 0.1196 | 0.4717 |
112
- | 0.5708 | 15.8279 | 11000 | 0.4334 | 0.1188 | 0.4757 |
113
- | 0.5575 | 16.1152 | 11200 | 0.4302 | 0.1178 | 0.4720 |
114
- | 0.5318 | 16.4032 | 11400 | 0.4299 | 0.1171 | 0.4697 |
115
- | 0.5593 | 16.6911 | 11600 | 0.4250 | 0.1155 | 0.4681 |
116
- | 0.5718 | 16.9791 | 11800 | 0.4248 | 0.1163 | 0.4692 |
117
- | 0.5748 | 17.2664 | 12000 | 0.4243 | 0.1154 | 0.4649 |
118
- | 0.5614 | 17.5544 | 12200 | 0.4232 | 0.1172 | 0.4727 |
119
- | 0.5359 | 17.8423 | 12400 | 0.4224 | 0.1149 | 0.4660 |
120
- | 0.5596 | 18.1296 | 12600 | 0.4199 | 0.1151 | 0.4651 |
121
- | 0.5315 | 18.4176 | 12800 | 0.4195 | 0.1149 | 0.4662 |
122
- | 0.5514 | 18.7055 | 13000 | 0.4195 | 0.1148 | 0.4655 |
123
- | 0.5629 | 18.9935 | 13200 | 0.4188 | 0.1151 | 0.4667 |
124
- | 0.5349 | 19.2808 | 13400 | 0.4184 | 0.1145 | 0.4626 |
125
- | 0.5468 | 19.5688 | 13600 | 0.4176 | 0.1149 | 0.4635 |
126
- | 0.5396 | 19.8567 | 13800 | 0.4177 | 0.1145 | 0.4635 |
127
 
128
 
129
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
 
14
 
15
  # ssc-bxk-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: 0.4698
20
+ - Cer: 0.1295
21
+ - Wer: 0.4903
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
+ | 0.4135 | 0.2436 | 200 | 0.4659 | 0.1308 | 0.5060 |
57
+ | 0.4426 | 0.4872 | 400 | 0.4867 | 0.1349 | 0.5145 |
58
+ | 0.4235 | 0.7308 | 600 | 0.4975 | 0.1362 | 0.5248 |
59
+ | 0.3909 | 0.9744 | 800 | 0.4877 | 0.1352 | 0.5119 |
60
+ | 0.3759 | 1.2180 | 1000 | 0.4774 | 0.1352 | 0.5163 |
61
+ | 0.3661 | 1.4616 | 1200 | 0.4770 | 0.1346 | 0.5103 |
62
+ | 0.3724 | 1.7052 | 1400 | 0.4820 | 0.1327 | 0.5110 |
63
+ | 0.3924 | 1.9488 | 1600 | 0.4854 | 0.1336 | 0.5032 |
64
+ | 0.3509 | 2.1924 | 1800 | 0.4763 | 0.1340 | 0.5094 |
65
+ | 0.3555 | 2.4361 | 2000 | 0.4774 | 0.1330 | 0.5037 |
66
+ | 0.3421 | 2.6797 | 2200 | 0.4973 | 0.1328 | 0.5073 |
67
+ | 0.3716 | 2.9233 | 2400 | 0.4815 | 0.1330 | 0.5021 |
68
+ | 0.3482 | 3.1669 | 2600 | 0.4833 | 0.1320 | 0.4996 |
69
+ | 0.3589 | 3.4105 | 2800 | 0.4659 | 0.1322 | 0.5021 |
70
+ | 0.3228 | 3.6541 | 3000 | 0.4796 | 0.1305 | 0.4922 |
71
+ | 0.3518 | 3.8977 | 3200 | 0.4706 | 0.1307 | 0.4954 |
72
+ | 0.3215 | 4.1413 | 3400 | 0.4803 | 0.1304 | 0.4933 |
73
+ | 0.305 | 4.3849 | 3600 | 0.4790 | 0.1304 | 0.4934 |
74
+ | 0.3045 | 4.6285 | 3800 | 0.4705 | 0.1305 | 0.4959 |
75
+ | 0.3256 | 4.8721 | 4000 | 0.4698 | 0.1295 | 0.4903 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
adapter.bxk.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c866df542b9ca3b1ae5a918f4721ab95d758898999ed9e739c7f5885b328a00
3
  size 9018880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eee6e4ea3d6973013205f0b7c0e48550654f0ec9a2a908df2ac68a9fc2cce0a
3
  size 9018880
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e754d283940b06f797389c5605de8e1ce75a7beb551c009f3f5b5a404f68c8ad
3
  size 3859111256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc5d03f86bcbbf2fd6d516566a08a1dc21fb6bdea5666fae1ddbc4e441ce4c8a
3
  size 3859111256
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a803ae205c1df45e89ea6504f0850538f95afc1473eca0bbff1c07cfab33684
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9793f462ec2e555b624c5a7be0890c70521e552dec302360a4a51f020fc08139
3
  size 5969