Hugging Face's logo

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

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
ctaguchi commited on
Commit
873103e
·
verified ·
1 Parent(s): 5ed7c67

End of training

Browse files
Files changed (4) hide show
  1. README.md +30 -76
  2. adapter.koo.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-koo-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: 0.5763
22
- - Cer: 0.1680
23
- - Wer: 0.6451
24
 
25
  ## Model description
26
 
@@ -40,86 +38,42 @@ 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
- | 1.5137 | 0.3046 | 200 | 1.0743 | 0.2808 | 0.8787 |
59
- | 1.1278 | 0.6093 | 400 | 0.9499 | 0.2464 | 0.8133 |
60
- | 1.1259 | 0.9139 | 600 | 0.9075 | 0.2356 | 0.7980 |
61
- | 1.0472 | 1.2178 | 800 | 0.8841 | 0.2379 | 0.8012 |
62
- | 1.0557 | 1.5225 | 1000 | 0.8607 | 0.2349 | 0.7847 |
63
- | 1.0558 | 1.8271 | 1200 | 0.8432 | 0.2302 | 0.7773 |
64
- | 0.9952 | 2.1310 | 1400 | 0.8185 | 0.2240 | 0.7584 |
65
- | 0.9826 | 2.4356 | 1600 | 0.8156 | 0.2199 | 0.7607 |
66
- | 0.9879 | 2.7403 | 1800 | 0.8231 | 0.2163 | 0.7497 |
67
- | 0.9952 | 3.0442 | 2000 | 0.7887 | 0.2183 | 0.7505 |
68
- | 0.9306 | 3.3488 | 2200 | 0.7941 | 0.2159 | 0.7387 |
69
- | 0.9802 | 3.6535 | 2400 | 0.7656 | 0.2130 | 0.7454 |
70
- | 1.0176 | 3.9581 | 2600 | 0.7604 | 0.2084 | 0.7261 |
71
- | 0.9297 | 4.2620 | 2800 | 0.7790 | 0.2086 | 0.7406 |
72
- | 0.9436 | 4.5666 | 3000 | 0.7517 | 0.2095 | 0.7408 |
73
- | 0.9693 | 4.8713 | 3200 | 0.7559 | 0.2249 | 0.7452 |
74
- | 0.8687 | 5.1752 | 3400 | 0.7327 | 0.2084 | 0.7353 |
75
- | 0.8501 | 5.4798 | 3600 | 0.7505 | 0.2054 | 0.7499 |
76
- | 0.9161 | 5.7845 | 3800 | 0.7379 | 0.1997 | 0.7166 |
77
- | 0.9541 | 6.0883 | 4000 | 0.7210 | 0.2073 | 0.7348 |
78
- | 0.8721 | 6.3930 | 4200 | 0.7261 | 0.2002 | 0.7117 |
79
- | 0.9356 | 6.6976 | 4400 | 0.6904 | 0.1949 | 0.7011 |
80
- | 0.8998 | 7.0015 | 4600 | 0.6905 | 0.1952 | 0.7073 |
81
- | 0.8969 | 7.3062 | 4800 | 0.6716 | 0.1914 | 0.7017 |
82
- | 0.8693 | 7.6108 | 5000 | 0.6736 | 0.1917 | 0.7019 |
83
- | 0.8978 | 7.9155 | 5200 | 0.6847 | 0.1916 | 0.7026 |
84
- | 0.8343 | 8.2193 | 5400 | 0.6828 | 0.1960 | 0.7140 |
85
- | 0.8527 | 8.5240 | 5600 | 0.6751 | 0.1939 | 0.7075 |
86
- | 0.8032 | 8.8286 | 5800 | 0.6568 | 0.1918 | 0.6903 |
87
- | 0.8541 | 9.1325 | 6000 | 0.6982 | 0.1969 | 0.7172 |
88
- | 0.8209 | 9.4372 | 6200 | 0.6421 | 0.1860 | 0.6935 |
89
- | 0.7728 | 9.7418 | 6400 | 0.6418 | 0.1868 | 0.6886 |
90
- | 0.8137 | 10.0457 | 6600 | 0.6456 | 0.1860 | 0.6911 |
91
- | 0.7723 | 10.3503 | 6800 | 0.6398 | 0.1852 | 0.6852 |
92
- | 0.8187 | 10.6550 | 7000 | 0.6547 | 0.1855 | 0.6890 |
93
- | 0.7836 | 10.9596 | 7200 | 0.6367 | 0.1833 | 0.6860 |
94
- | 0.7864 | 11.2635 | 7400 | 0.6448 | 0.1841 | 0.6837 |
95
- | 0.8003 | 11.5682 | 7600 | 0.6299 | 0.1807 | 0.6854 |
96
- | 0.7817 | 11.8728 | 7800 | 0.6245 | 0.1855 | 0.6884 |
97
- | 0.7387 | 12.1767 | 8000 | 0.6154 | 0.1817 | 0.6776 |
98
- | 0.7685 | 12.4813 | 8200 | 0.6330 | 0.1804 | 0.6788 |
99
- | 0.7789 | 12.7860 | 8400 | 0.6076 | 0.1774 | 0.6580 |
100
- | 0.731 | 13.0899 | 8600 | 0.6056 | 0.1768 | 0.6633 |
101
- | 0.7256 | 13.3945 | 8800 | 0.6119 | 0.1779 | 0.6729 |
102
- | 0.707 | 13.6992 | 9000 | 0.6169 | 0.1787 | 0.6678 |
103
- | 0.7594 | 14.0030 | 9200 | 0.6089 | 0.1762 | 0.6578 |
104
- | 0.7542 | 14.3077 | 9400 | 0.6126 | 0.1787 | 0.6703 |
105
- | 0.7337 | 14.6123 | 9600 | 0.5991 | 0.1765 | 0.6697 |
106
- | 0.7228 | 14.9170 | 9800 | 0.5952 | 0.1730 | 0.6674 |
107
- | 0.7603 | 15.2209 | 10000 | 0.6016 | 0.1763 | 0.6648 |
108
- | 0.7238 | 15.5255 | 10200 | 0.5947 | 0.1749 | 0.6599 |
109
- | 0.7145 | 15.8302 | 10400 | 0.5934 | 0.1718 | 0.6538 |
110
- | 0.6758 | 16.1340 | 10600 | 0.5881 | 0.1732 | 0.6648 |
111
- | 0.7091 | 16.4387 | 10800 | 0.5985 | 0.1723 | 0.6617 |
112
- | 0.7195 | 16.7433 | 11000 | 0.5846 | 0.1700 | 0.6512 |
113
- | 0.6882 | 17.0472 | 11200 | 0.5884 | 0.1717 | 0.6534 |
114
- | 0.702 | 17.3519 | 11400 | 0.5869 | 0.1699 | 0.6495 |
115
- | 0.7373 | 17.6565 | 11600 | 0.5819 | 0.1706 | 0.6540 |
116
- | 0.6971 | 17.9612 | 11800 | 0.5768 | 0.1699 | 0.6534 |
117
- | 0.6595 | 18.2650 | 12000 | 0.5801 | 0.1686 | 0.6519 |
118
- | 0.7114 | 18.5697 | 12200 | 0.5814 | 0.1692 | 0.6502 |
119
- | 0.6836 | 18.8743 | 12400 | 0.5790 | 0.1684 | 0.6472 |
120
- | 0.6843 | 19.1782 | 12600 | 0.5782 | 0.1674 | 0.6453 |
121
- | 0.6761 | 19.4829 | 12800 | 0.5768 | 0.1683 | 0.6457 |
122
- | 0.6896 | 19.7875 | 13000 | 0.5763 | 0.1680 | 0.6451 |
123
 
124
 
125
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
 
14
 
15
  # ssc-koo-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: 0.6290
20
+ - Cer: 0.1809
21
+ - Wer: 0.6529
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
+ | 0.5026 | 0.2380 | 200 | 0.6692 | 0.1832 | 0.6723 |
57
+ | 0.6058 | 0.4759 | 400 | 0.8334 | 0.1979 | 0.6920 |
58
+ | 0.5705 | 0.7139 | 600 | 0.6837 | 0.1920 | 0.6888 |
59
+ | 1.0209 | 0.9518 | 800 | 0.6648 | 0.1911 | 0.6960 |
60
+ | 0.7044 | 1.1892 | 1000 | 0.7074 | 0.1910 | 0.6812 |
61
+ | 0.5302 | 1.4271 | 1200 | 0.6980 | 0.1860 | 0.6689 |
62
+ | 0.665 | 1.6651 | 1400 | 0.6648 | 0.1885 | 0.6801 |
63
+ | 0.4785 | 1.9030 | 1600 | 0.7247 | 0.1888 | 0.6739 |
64
+ | 0.5647 | 2.1404 | 1800 | 0.6650 | 0.1870 | 0.6773 |
65
+ | 0.4752 | 2.3783 | 2000 | 0.6739 | 0.1855 | 0.6705 |
66
+ | 0.5433 | 2.6163 | 2200 | 0.6602 | 0.1875 | 0.6805 |
67
+ | 0.4533 | 2.8543 | 2400 | 0.6522 | 0.1861 | 0.6765 |
68
+ | 0.5059 | 3.0916 | 2600 | 0.6833 | 0.1833 | 0.6657 |
69
+ | 0.4554 | 3.3296 | 2800 | 0.7033 | 0.1859 | 0.6653 |
70
+ | 0.4887 | 3.5675 | 3000 | 0.6642 | 0.1867 | 0.6763 |
71
+ | 0.4191 | 3.8055 | 3200 | 0.6398 | 0.1825 | 0.6616 |
72
+ | 0.5062 | 4.0428 | 3400 | 0.6492 | 0.1809 | 0.6519 |
73
+ | 0.503 | 4.2808 | 3600 | 0.6400 | 0.1834 | 0.6561 |
74
+ | 0.4721 | 4.5187 | 3800 | 0.6272 | 0.1805 | 0.6585 |
75
+ | 0.4679 | 4.7567 | 4000 | 0.6303 | 0.1804 | 0.6542 |
76
+ | 0.4593 | 4.9946 | 4200 | 0.6290 | 0.1809 | 0.6529 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
 
78
 
79
  ### Framework versions
adapter.koo.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1262fd265a1f6a3e309db992ecdd1381172b0a9b95a86422fd731915cbd2415a
3
  size 9008632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63495ac7c82209f2c5e0260839c82daf17ea5b00b80348c9d605526f2b289c1d
3
  size 9008632
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ee6a8278c89713778a0301799e11a67e6aaaffda6279841cb93ed7c68b47b14
3
  size 3859101008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d47f04cdb34ca3ab04683258f6651557cbf2e563cbc64c8ae8aa351ce27a9e95
3
  size 3859101008
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8642486932b4dee4713b6425b9eed0f1c27d4389ff8382b780e385711459339e
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6ce8767b49745f499de06d0612ca077031816c72d58a9f410d35d9e8cb8761
3
  size 5969