Hugging Face's logo

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

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
ctaguchi commited on
Commit
4ec040d
·
verified ·
1 Parent(s): 457cb0e

End of training

Browse files
Files changed (4) hide show
  1. README.md +31 -85
  2. adapter.pne.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-pne-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: 0.3988
22
- - Cer: 0.1116
23
- - Wer: 0.3299
24
 
25
  ## Model description
26
 
@@ -40,95 +38,43 @@ 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
- | 1.2889 | 0.2685 | 200 | 0.8402 | 0.2271 | 0.6489 |
59
- | 1.0716 | 0.5369 | 400 | 0.6725 | 0.1834 | 0.5259 |
60
- | 0.9362 | 0.8054 | 600 | 0.6121 | 0.1678 | 0.4840 |
61
- | 0.89 | 1.0738 | 800 | 0.5791 | 0.1584 | 0.4544 |
62
- | 0.8681 | 1.3423 | 1000 | 0.5532 | 0.1530 | 0.4397 |
63
- | 0.8789 | 1.6107 | 1200 | 0.5536 | 0.1538 | 0.4418 |
64
- | 0.8424 | 1.8792 | 1400 | 0.5269 | 0.1464 | 0.4200 |
65
- | 0.826 | 2.1477 | 1600 | 0.5185 | 0.1424 | 0.4075 |
66
- | 0.8315 | 2.4161 | 1800 | 0.5052 | 0.1396 | 0.4019 |
67
- | 0.8123 | 2.6846 | 2000 | 0.5048 | 0.1379 | 0.3952 |
68
- | 0.8159 | 2.9530 | 2200 | 0.4888 | 0.1363 | 0.3919 |
69
- | 0.7834 | 3.2215 | 2400 | 0.4804 | 0.1347 | 0.3854 |
70
- | 0.7479 | 3.4899 | 2600 | 0.4968 | 0.1371 | 0.3953 |
71
- | 0.7565 | 3.7584 | 2800 | 0.4762 | 0.1315 | 0.3734 |
72
- | 0.7769 | 4.0268 | 3000 | 0.4869 | 0.1315 | 0.3744 |
73
- | 0.702 | 4.2953 | 3200 | 0.4835 | 0.1317 | 0.3775 |
74
- | 0.7573 | 4.5638 | 3400 | 0.4771 | 0.1295 | 0.3676 |
75
- | 0.7165 | 4.8322 | 3600 | 0.4696 | 0.1272 | 0.3646 |
76
- | 0.7126 | 5.1007 | 3800 | 0.4942 | 0.1339 | 0.3843 |
77
- | 0.7197 | 5.3691 | 4000 | 0.4670 | 0.1268 | 0.3628 |
78
- | 0.7472 | 5.6376 | 4200 | 0.4651 | 0.1273 | 0.3646 |
79
- | 0.7005 | 5.9060 | 4400 | 0.4690 | 0.1316 | 0.3830 |
80
- | 0.7072 | 6.1745 | 4600 | 0.4853 | 0.1306 | 0.3767 |
81
- | 0.6864 | 6.4430 | 4800 | 0.4825 | 0.1261 | 0.3587 |
82
- | 0.6764 | 6.7114 | 5000 | 0.4550 | 0.1258 | 0.3614 |
83
- | 0.763 | 6.9799 | 5200 | 0.4843 | 0.1281 | 0.3678 |
84
- | 0.7177 | 7.2483 | 5400 | 0.4715 | 0.1276 | 0.3667 |
85
- | 0.6742 | 7.5168 | 5600 | 0.4600 | 0.1248 | 0.3589 |
86
- | 0.6795 | 7.7852 | 5800 | 0.5308 | 0.1275 | 0.3692 |
87
- | 0.7109 | 8.0537 | 6000 | 0.4499 | 0.1226 | 0.3550 |
88
- | 0.6684 | 8.3221 | 6200 | 0.4773 | 0.1299 | 0.3773 |
89
- | 0.6827 | 8.5906 | 6400 | 0.4802 | 0.1260 | 0.3631 |
90
- | 0.6555 | 8.8591 | 6600 | 0.4561 | 0.1249 | 0.3611 |
91
- | 0.6481 | 9.1275 | 6800 | 0.4601 | 0.1302 | 0.3848 |
92
- | 0.6913 | 9.3960 | 7000 | 0.4303 | 0.1184 | 0.3415 |
93
- | 0.661 | 9.6644 | 7200 | 0.4449 | 0.1193 | 0.3452 |
94
- | 0.628 | 9.9329 | 7400 | 0.4491 | 0.1213 | 0.3518 |
95
- | 0.6669 | 10.2013 | 7600 | 0.4299 | 0.1185 | 0.3446 |
96
- | 0.6471 | 10.4698 | 7800 | 0.4364 | 0.1210 | 0.3531 |
97
- | 0.6254 | 10.7383 | 8000 | 0.4457 | 0.1240 | 0.3642 |
98
- | 0.6406 | 11.0067 | 8200 | 0.4365 | 0.1199 | 0.3503 |
99
- | 0.6053 | 11.2752 | 8400 | 0.4365 | 0.1162 | 0.3345 |
100
- | 0.6322 | 11.5436 | 8600 | 0.4191 | 0.1171 | 0.3405 |
101
- | 0.6391 | 11.8121 | 8800 | 0.4088 | 0.1141 | 0.3289 |
102
- | 0.6205 | 12.0805 | 9000 | 0.4149 | 0.1141 | 0.3301 |
103
- | 0.6313 | 12.3490 | 9200 | 0.4185 | 0.1171 | 0.3431 |
104
- | 0.6017 | 12.6174 | 9400 | 0.4075 | 0.1157 | 0.3400 |
105
- | 0.6437 | 12.8859 | 9600 | 0.4050 | 0.1132 | 0.3292 |
106
- | 0.6354 | 13.1544 | 9800 | 0.4087 | 0.1153 | 0.3359 |
107
- | 0.6149 | 13.4228 | 10000 | 0.4035 | 0.1134 | 0.3267 |
108
- | 0.6002 | 13.6913 | 10200 | 0.3985 | 0.1135 | 0.3292 |
109
- | 0.6098 | 13.9597 | 10400 | 0.4298 | 0.1180 | 0.3492 |
110
- | 0.5787 | 14.2282 | 10600 | 0.4065 | 0.1144 | 0.3333 |
111
- | 0.6282 | 14.4966 | 10800 | 0.4057 | 0.1149 | 0.3358 |
112
- | 0.5775 | 14.7651 | 11000 | 0.4188 | 0.1175 | 0.3471 |
113
- | 0.595 | 15.0336 | 11200 | 0.4063 | 0.1144 | 0.3354 |
114
- | 0.6184 | 15.3020 | 11400 | 0.4004 | 0.1125 | 0.3300 |
115
- | 0.5909 | 15.5705 | 11600 | 0.4156 | 0.1157 | 0.3431 |
116
- | 0.5826 | 15.8389 | 11800 | 0.4147 | 0.1172 | 0.3476 |
117
- | 0.5858 | 16.1074 | 12000 | 0.4010 | 0.1129 | 0.3346 |
118
- | 0.5793 | 16.3758 | 12200 | 0.3852 | 0.1089 | 0.3154 |
119
- | 0.5661 | 16.6443 | 12400 | 0.3964 | 0.1109 | 0.3229 |
120
- | 0.5861 | 16.9128 | 12600 | 0.3976 | 0.1120 | 0.3283 |
121
- | 0.585 | 17.1812 | 12800 | 0.3937 | 0.1108 | 0.3231 |
122
- | 0.5873 | 17.4497 | 13000 | 0.4106 | 0.1142 | 0.3392 |
123
- | 0.5572 | 17.7181 | 13200 | 0.3959 | 0.1120 | 0.3320 |
124
- | 0.5958 | 17.9866 | 13400 | 0.4018 | 0.1118 | 0.3301 |
125
- | 0.5597 | 18.2550 | 13600 | 0.3958 | 0.1129 | 0.3347 |
126
- | 0.5559 | 18.5235 | 13800 | 0.3987 | 0.1105 | 0.3255 |
127
- | 0.5951 | 18.7919 | 14000 | 0.3957 | 0.1097 | 0.3217 |
128
- | 0.5752 | 19.0604 | 14200 | 0.3935 | 0.1116 | 0.3298 |
129
- | 0.5571 | 19.3289 | 14400 | 0.4006 | 0.1115 | 0.3292 |
130
- | 0.5683 | 19.5973 | 14600 | 0.4020 | 0.1122 | 0.3329 |
131
- | 0.5625 | 19.8658 | 14800 | 0.3988 | 0.1116 | 0.3299 |
132
 
133
 
134
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
 
14
 
15
  # ssc-pne-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: 0.3953
20
+ - Cer: 0.1118
21
+ - Wer: 0.3139
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
+ | 0.4422 | 0.2209 | 200 | 0.4046 | 0.1166 | 0.3444 |
57
+ | 0.4907 | 0.4417 | 400 | 0.4135 | 0.1214 | 0.3548 |
58
+ | 0.4654 | 0.6626 | 600 | 0.4047 | 0.1156 | 0.3324 |
59
+ | 0.4416 | 0.8835 | 800 | 0.4082 | 0.1171 | 0.3335 |
60
+ | 0.4588 | 1.1038 | 1000 | 0.4119 | 0.1159 | 0.3318 |
61
+ | 0.4282 | 1.3247 | 1200 | 0.4149 | 0.1178 | 0.3322 |
62
+ | 0.4215 | 1.5456 | 1400 | 0.4102 | 0.1160 | 0.3279 |
63
+ | 0.4474 | 1.7664 | 1600 | 0.4108 | 0.1149 | 0.3258 |
64
+ | 0.3888 | 1.9873 | 1800 | 0.4078 | 0.1154 | 0.3246 |
65
+ | 0.3937 | 2.2076 | 2000 | 0.4127 | 0.1148 | 0.3224 |
66
+ | 0.3796 | 2.4285 | 2200 | 0.4112 | 0.1154 | 0.3266 |
67
+ | 0.3988 | 2.6494 | 2400 | 0.4091 | 0.1154 | 0.3244 |
68
+ | 0.4194 | 2.8702 | 2600 | 0.4052 | 0.1158 | 0.3231 |
69
+ | 0.394 | 3.0906 | 2800 | 0.4022 | 0.1149 | 0.3230 |
70
+ | 0.4042 | 3.3114 | 3000 | 0.4043 | 0.1141 | 0.3190 |
71
+ | 0.3235 | 3.5323 | 3200 | 0.3982 | 0.1138 | 0.3207 |
72
+ | 0.3295 | 3.7532 | 3400 | 0.4004 | 0.1128 | 0.3164 |
73
+ | 0.361 | 3.9740 | 3600 | 0.4003 | 0.1125 | 0.3151 |
74
+ | 0.3303 | 4.1944 | 3800 | 0.3976 | 0.1123 | 0.3144 |
75
+ | 0.3694 | 4.4152 | 4000 | 0.3931 | 0.1125 | 0.3150 |
76
+ | 0.3562 | 4.6361 | 4200 | 0.3933 | 0.1117 | 0.3149 |
77
+ | 0.3177 | 4.8570 | 4400 | 0.3953 | 0.1118 | 0.3139 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
adapter.pne.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bf11fe335d6da117be72eff76cbf89ecd6e056af3ba9a3b41b723aae397082f
3
  size 8926640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6317684c067f37943cbd43e20c5d2d621b508be5b35abb405d0101f4da0375
3
  size 8926640
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a93f35a9d7d87f81604e81c43186e876d51b2101a7dd1c36090f83cd984b1ba
3
  size 3859019024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f197b742936f4df7c0919c99f3da0821591f8e191f6d47a1ffb600f83629e631
3
  size 3859019024
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:479cce9cc5b493ecaa2805e81220df867b1f949a02ed9d00d65827f01ce4af8b
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02dc5664f220f2d64a1e25a47e533dd38d84b1524cfe1666005238062400827f
3
  size 5969