Hugging Face's logo

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

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
ctaguchi commited on
Commit
fc1faaa
·
verified ·
1 Parent(s): ccdc290

End of training

Browse files
Files changed (4) hide show
  1. README.md +19 -65
  2. adapter.hch.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-hch-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: 0.3053
22
- - Cer: 0.1045
23
- - Wer: 0.6115
24
 
25
  ## Model description
26
 
@@ -40,75 +38,31 @@ 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
- | 1.4276 | 0.3660 | 200 | 0.9544 | 0.2735 | 0.9803 |
59
- | 1.161 | 0.7319 | 400 | 0.7525 | 0.2255 | 0.9350 |
60
- | 1.0239 | 1.0970 | 600 | 0.6291 | 0.2027 | 0.9035 |
61
- | 1.0017 | 1.4629 | 800 | 0.6006 | 0.1892 | 0.8764 |
62
- | 0.9205 | 1.8289 | 1000 | 0.5486 | 0.1751 | 0.8497 |
63
- | 0.8995 | 2.1940 | 1200 | 0.5242 | 0.1767 | 0.8525 |
64
- | 0.826 | 2.5599 | 1400 | 0.4803 | 0.1651 | 0.8168 |
65
- | 0.883 | 2.9259 | 1600 | 0.4681 | 0.1631 | 0.8080 |
66
- | 0.8183 | 3.2909 | 1800 | 0.4751 | 0.1525 | 0.7907 |
67
- | 0.8069 | 3.6569 | 2000 | 0.4530 | 0.1571 | 0.7835 |
68
- | 0.7999 | 4.0220 | 2200 | 0.4156 | 0.1456 | 0.7588 |
69
- | 0.7343 | 4.3879 | 2400 | 0.4135 | 0.1398 | 0.7347 |
70
- | 0.7828 | 4.7539 | 2600 | 0.4156 | 0.1402 | 0.7455 |
71
- | 0.6965 | 5.1189 | 2800 | 0.4064 | 0.1375 | 0.7383 |
72
- | 0.7361 | 5.4849 | 3000 | 0.3888 | 0.1362 | 0.7316 |
73
- | 0.7471 | 5.8509 | 3200 | 0.3795 | 0.1316 | 0.7148 |
74
- | 0.6734 | 6.2159 | 3400 | 0.3919 | 0.1313 | 0.7085 |
75
- | 0.6824 | 6.5819 | 3600 | 0.3979 | 0.1280 | 0.7089 |
76
- | 0.6755 | 6.9478 | 3800 | 0.3972 | 0.1287 | 0.7029 |
77
- | 0.6782 | 7.3129 | 4000 | 0.4095 | 0.1269 | 0.6907 |
78
- | 0.6285 | 7.6789 | 4200 | 0.4088 | 0.1284 | 0.6932 |
79
- | 0.6501 | 8.0439 | 4400 | 0.3619 | 0.1247 | 0.6881 |
80
- | 0.6508 | 8.4099 | 4600 | 0.3708 | 0.1257 | 0.6886 |
81
- | 0.6154 | 8.7758 | 4800 | 0.3512 | 0.1227 | 0.6795 |
82
- | 0.5889 | 9.1409 | 5000 | 0.3874 | 0.1215 | 0.6694 |
83
- | 0.6095 | 9.5069 | 5200 | 0.3942 | 0.1247 | 0.6842 |
84
- | 0.6149 | 9.8728 | 5400 | 0.3711 | 0.1198 | 0.6641 |
85
- | 0.5771 | 10.2379 | 5600 | 0.3817 | 0.1189 | 0.6550 |
86
- | 0.6132 | 10.6038 | 5800 | 0.3287 | 0.1182 | 0.6562 |
87
- | 0.5934 | 10.9698 | 6000 | 0.3257 | 0.1142 | 0.6550 |
88
- | 0.5774 | 11.3349 | 6200 | 0.3352 | 0.1170 | 0.6571 |
89
- | 0.5632 | 11.7008 | 6400 | 0.3274 | 0.1131 | 0.6425 |
90
- | 0.5534 | 12.0659 | 6600 | 0.3450 | 0.1161 | 0.6476 |
91
- | 0.5547 | 12.4318 | 6800 | 0.3396 | 0.1136 | 0.6453 |
92
- | 0.5281 | 12.7978 | 7000 | 0.3411 | 0.1136 | 0.6411 |
93
- | 0.5361 | 13.1629 | 7200 | 0.3187 | 0.1111 | 0.6450 |
94
- | 0.5335 | 13.5288 | 7400 | 0.2954 | 0.1111 | 0.6372 |
95
- | 0.5424 | 13.8948 | 7600 | 0.3327 | 0.1109 | 0.6399 |
96
- | 0.5248 | 14.2598 | 7800 | 0.3223 | 0.1119 | 0.6377 |
97
- | 0.5281 | 14.6258 | 8000 | 0.3159 | 0.1110 | 0.6296 |
98
- | 0.5291 | 14.9918 | 8200 | 0.3163 | 0.1086 | 0.6302 |
99
- | 0.5076 | 15.3568 | 8400 | 0.3148 | 0.1080 | 0.6230 |
100
- | 0.5189 | 15.7228 | 8600 | 0.3256 | 0.1084 | 0.6230 |
101
- | 0.5173 | 16.0878 | 8800 | 0.3157 | 0.1093 | 0.6267 |
102
- | 0.5077 | 16.4538 | 9000 | 0.3076 | 0.1072 | 0.6203 |
103
- | 0.4914 | 16.8198 | 9200 | 0.3051 | 0.1066 | 0.6205 |
104
- | 0.4983 | 17.1848 | 9400 | 0.3137 | 0.1071 | 0.6237 |
105
- | 0.5008 | 17.5508 | 9600 | 0.3192 | 0.1072 | 0.6161 |
106
- | 0.4766 | 17.9167 | 9800 | 0.3039 | 0.1061 | 0.6168 |
107
- | 0.4845 | 18.2818 | 10000 | 0.3179 | 0.1060 | 0.6164 |
108
- | 0.4955 | 18.6478 | 10200 | 0.3164 | 0.1049 | 0.6133 |
109
- | 0.466 | 19.0128 | 10400 | 0.3124 | 0.1045 | 0.6129 |
110
- | 0.4639 | 19.3788 | 10600 | 0.3071 | 0.1045 | 0.6115 |
111
- | 0.4944 | 19.7447 | 10800 | 0.3053 | 0.1045 | 0.6115 |
112
 
113
 
114
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
 
14
 
15
  # ssc-hch-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: 0.2614
20
+ - Cer: 0.1088
21
+ - Wer: 0.6374
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
+ | 0.3141 | 0.4739 | 200 | 0.2800 | 0.1156 | 0.6619 |
57
+ | 0.3367 | 0.9479 | 400 | 0.2720 | 0.1125 | 0.6523 |
58
+ | 0.2839 | 1.4218 | 600 | 0.2836 | 0.1166 | 0.6643 |
59
+ | 0.3091 | 1.8957 | 800 | 0.2665 | 0.1116 | 0.6487 |
60
+ | 0.2442 | 2.3697 | 1000 | 0.2818 | 0.1131 | 0.6497 |
61
+ | 0.249 | 2.8436 | 1200 | 0.2785 | 0.1124 | 0.6550 |
62
+ | 0.2169 | 3.3175 | 1400 | 0.2674 | 0.1117 | 0.6481 |
63
+ | 0.2255 | 3.7915 | 1600 | 0.2593 | 0.1092 | 0.6400 |
64
+ | 0.2075 | 4.2654 | 1800 | 0.2625 | 0.1087 | 0.6307 |
65
+ | 0.2047 | 4.7393 | 2000 | 0.2614 | 0.1088 | 0.6374 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
adapter.hch.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fdf1d2bc8239d350d1b554e7f4d68e2205315cfea5d0f2010c9c1b9425bdee2
3
  size 9039376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67c6018f9fbb8aa32f9fc0e180175d2cafb4a38ce6313576914c270e827c7687
3
  size 9039376
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9358b9de9159993b6418f1220d2f1295677b122b80ad79c54e2d930a3e273636
3
  size 3859131752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:902cad9825dc98092f4cacd4b13877d2a82219a0117d332e656f184afb0f336a
3
  size 3859131752
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d335b454df421db5ceb9b2a0114bb03910d4ef655f3315824d663d0655e31ab0
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8acd04a79c8eff7da1d5b4f873c5b8ca6d8650d6128c5fb792e84b9212399cdd
3
  size 5969