Hugging Face's logo

tuanio
/
fine-w2v2base-bs16-ep100-lr2e-05-linguistic-rmsnorm-focal_ctc_a0.75_g1.0-0.05_10_0.004_40

Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files Community
tuanio commited on
Commit
5243e31
·
1 Parent(s): c18063f

Model save

Browse files
Files changed (2) hide show
  1. README.md +170 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: nguyenvulebinh/wav2vec2-base-vietnamese-250h
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: fine-w2v2base-bs16-ep100-lr2e-05-linguistic-rmsnorm-focal_ctc_a0.75_g1.0-0.05_10_0.004_40
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # fine-w2v2base-bs16-ep100-lr2e-05-linguistic-rmsnorm-focal_ctc_a0.75_g1.0-0.05_10_0.004_40
17
+
18
+ This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vietnamese-250h](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 3.1907
21
+ - Wer: 0.1001
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 64
47
+ - total_eval_batch_size: 32
48
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 100
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
+ | 1628.3266 | 0.94 | 50 | 795.4863 | 15.7055 |
58
+ | 1167.4639 | 1.89 | 100 | 276.5289 | 0.9954 |
59
+ | 193.5269 | 2.83 | 150 | 67.2639 | 1.0 |
60
+ | 86.2802 | 3.77 | 200 | 63.6259 | 1.0 |
61
+ | 82.8944 | 4.72 | 250 | 61.8939 | 1.0 |
62
+ | 79.9575 | 5.66 | 300 | 59.7914 | 1.0 |
63
+ | 77.3429 | 6.6 | 350 | 58.1507 | 1.0 |
64
+ | 74.0584 | 7.55 | 400 | 57.2977 | 1.0 |
65
+ | 72.6694 | 8.49 | 450 | 56.7115 | 1.0 |
66
+ | 73.417 | 9.43 | 500 | 56.6074 | 1.0 |
67
+ | 72.4291 | 10.38 | 550 | 56.4755 | 1.0 |
68
+ | 72.7847 | 11.32 | 600 | 56.8623 | 1.0 |
69
+ | 69.3297 | 12.26 | 650 | 49.6540 | 0.9637 |
70
+ | 54.2644 | 13.21 | 700 | 29.1559 | 0.5631 |
71
+ | 31.2303 | 14.15 | 750 | 13.8957 | 0.2414 |
72
+ | 19.4522 | 15.09 | 800 | 9.7460 | 0.1949 |
73
+ | 15.0046 | 16.04 | 850 | 7.6735 | 0.1622 |
74
+ | 12.3783 | 16.98 | 900 | 6.5559 | 0.1520 |
75
+ | 10.7256 | 17.92 | 950 | 5.7852 | 0.1423 |
76
+ | 9.8218 | 18.87 | 1000 | 5.4473 | 0.1395 |
77
+ | 9.0115 | 19.81 | 1050 | 5.1250 | 0.1356 |
78
+ | 8.1076 | 20.75 | 1100 | 4.7980 | 0.1233 |
79
+ | 7.9779 | 21.7 | 1150 | 4.6150 | 0.1211 |
80
+ | 7.6027 | 22.64 | 1200 | 4.6507 | 0.1251 |
81
+ | 7.4535 | 23.58 | 1250 | 4.4814 | 0.1210 |
82
+ | 6.946 | 24.53 | 1300 | 4.4369 | 0.1149 |
83
+ | 7.0627 | 25.47 | 1350 | 4.1153 | 0.1139 |
84
+ | 6.2482 | 26.42 | 1400 | 4.0045 | 0.1101 |
85
+ | 6.2238 | 27.36 | 1450 | 4.0355 | 0.1158 |
86
+ | 5.8919 | 28.3 | 1500 | 3.9625 | 0.1154 |
87
+ | 5.7955 | 29.25 | 1550 | 3.7957 | 0.1127 |
88
+ | 5.4849 | 30.19 | 1600 | 3.7986 | 0.1058 |
89
+ | 5.1108 | 31.13 | 1650 | 3.8188 | 0.1070 |
90
+ | 5.3354 | 32.08 | 1700 | 3.6909 | 0.1024 |
91
+ | 5.1149 | 33.02 | 1750 | 3.6227 | 0.1023 |
92
+ | 4.976 | 33.96 | 1800 | 3.6176 | 0.1016 |
93
+ | 4.5904 | 34.91 | 1850 | 3.5959 | 0.1079 |
94
+ | 4.6613 | 35.85 | 1900 | 3.5000 | 0.1069 |
95
+ | 4.7697 | 36.79 | 1950 | 3.5211 | 0.1014 |
96
+ | 4.4224 | 37.74 | 2000 | 3.4720 | 0.1001 |
97
+ | 4.5255 | 38.68 | 2050 | 3.4178 | 0.0983 |
98
+ | 4.2808 | 39.62 | 2100 | 3.4801 | 0.1044 |
99
+ | 4.2407 | 40.57 | 2150 | 3.4080 | 0.1000 |
100
+ | 3.9611 | 41.51 | 2200 | 3.4514 | 0.1049 |
101
+ | 4.014 | 42.45 | 2250 | 3.3983 | 0.1089 |
102
+ | 3.8487 | 43.4 | 2300 | 3.4164 | 0.1042 |
103
+ | 3.8132 | 44.34 | 2350 | 3.3562 | 0.0958 |
104
+ | 3.6973 | 45.28 | 2400 | 3.2839 | 0.0978 |
105
+ | 3.606 | 46.23 | 2450 | 3.3125 | 0.1009 |
106
+ | 3.5412 | 47.17 | 2500 | 3.2580 | 0.0977 |
107
+ | 3.3971 | 48.11 | 2550 | 3.3065 | 0.0984 |
108
+ | 3.4795 | 49.06 | 2600 | 3.3312 | 0.1037 |
109
+ | 3.302 | 50.0 | 2650 | 3.3015 | 0.0986 |
110
+ | 3.2486 | 50.94 | 2700 | 3.2506 | 0.0977 |
111
+ | 3.3977 | 51.89 | 2750 | 3.2406 | 0.0952 |
112
+ | 3.0229 | 52.83 | 2800 | 3.2880 | 0.0989 |
113
+ | 3.2615 | 53.77 | 2850 | 3.3112 | 0.0998 |
114
+ | 3.2023 | 54.72 | 2900 | 3.2895 | 0.1037 |
115
+ | 3.0037 | 55.66 | 2950 | 3.3394 | 0.1018 |
116
+ | 2.9249 | 56.6 | 3000 | 3.2351 | 0.0974 |
117
+ | 3.112 | 57.55 | 3050 | 3.2868 | 0.1019 |
118
+ | 3.0261 | 58.49 | 3100 | 3.3241 | 0.1039 |
119
+ | 2.8959 | 59.43 | 3150 | 3.2251 | 0.0947 |
120
+ | 2.946 | 60.38 | 3200 | 3.2880 | 0.1012 |
121
+ | 2.6933 | 61.32 | 3250 | 3.2595 | 0.1031 |
122
+ | 2.8755 | 62.26 | 3300 | 3.2140 | 0.1048 |
123
+ | 2.606 | 63.21 | 3350 | 3.2743 | 0.1075 |
124
+ | 2.7607 | 64.15 | 3400 | 3.2455 | 0.1053 |
125
+ | 2.6394 | 65.09 | 3450 | 3.2335 | 0.0994 |
126
+ | 2.6899 | 66.04 | 3500 | 3.2278 | 0.1004 |
127
+ | 2.719 | 66.98 | 3550 | 3.2012 | 0.0979 |
128
+ | 2.6997 | 67.92 | 3600 | 3.2009 | 0.0979 |
129
+ | 2.5935 | 68.87 | 3650 | 3.2141 | 0.0978 |
130
+ | 2.6115 | 69.81 | 3700 | 3.1760 | 0.0947 |
131
+ | 2.5713 | 70.75 | 3750 | 3.1937 | 0.0977 |
132
+ | 2.6647 | 71.7 | 3800 | 3.1629 | 0.0986 |
133
+ | 2.4878 | 72.64 | 3850 | 3.1675 | 0.0952 |
134
+ | 2.4761 | 73.58 | 3900 | 3.1951 | 0.0976 |
135
+ | 2.3124 | 74.53 | 3950 | 3.1629 | 0.0954 |
136
+ | 2.5718 | 75.47 | 4000 | 3.1577 | 0.0978 |
137
+ | 2.4606 | 76.42 | 4050 | 3.1632 | 0.0973 |
138
+ | 2.5313 | 77.36 | 4100 | 3.1841 | 0.0988 |
139
+ | 2.5124 | 78.3 | 4150 | 3.1894 | 0.0987 |
140
+ | 2.3324 | 79.25 | 4200 | 3.1719 | 0.0966 |
141
+ | 2.4468 | 80.19 | 4250 | 3.1760 | 0.0964 |
142
+ | 2.4035 | 81.13 | 4300 | 3.2014 | 0.0983 |
143
+ | 2.3834 | 82.08 | 4350 | 3.1823 | 0.0966 |
144
+ | 2.3655 | 83.02 | 4400 | 3.1758 | 0.0948 |
145
+ | 2.3525 | 83.96 | 4450 | 3.1921 | 0.0980 |
146
+ | 2.4428 | 84.91 | 4500 | 3.1990 | 0.0970 |
147
+ | 2.3276 | 85.85 | 4550 | 3.1907 | 0.0984 |
148
+ | 2.4423 | 86.79 | 4600 | 3.1893 | 0.0977 |
149
+ | 2.3457 | 87.74 | 4650 | 3.2001 | 0.1005 |
150
+ | 2.4146 | 88.68 | 4700 | 3.1883 | 0.0985 |
151
+ | 2.3415 | 89.62 | 4750 | 3.1934 | 0.0997 |
152
+ | 2.2057 | 90.57 | 4800 | 3.1939 | 0.0995 |
153
+ | 2.5141 | 91.51 | 4850 | 3.1944 | 0.1006 |
154
+ | 2.175 | 92.45 | 4900 | 3.1808 | 0.0986 |
155
+ | 2.4668 | 93.4 | 4950 | 3.1885 | 0.0994 |
156
+ | 2.2732 | 94.34 | 5000 | 3.1877 | 0.0998 |
157
+ | 2.2636 | 95.28 | 5050 | 3.1877 | 0.0989 |
158
+ | 2.3504 | 96.23 | 5100 | 3.1904 | 0.1000 |
159
+ | 2.2721 | 97.17 | 5150 | 3.1917 | 0.1005 |
160
+ | 2.4014 | 98.11 | 5200 | 3.1922 | 0.1003 |
161
+ | 2.3263 | 99.06 | 5250 | 3.1897 | 0.0998 |
162
+ | 2.3731 | 100.0 | 5300 | 3.1907 | 0.1001 |
163
+
164
+
165
+ ### Framework versions
166
+
167
+ - Transformers 4.34.0
168
+ - Pytorch 2.0.1
169
+ - Datasets 2.14.5
170
+ - Tokenizers 0.14.1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b3395674019e1092c5df5a27bb310c111ee262f0b4f577617a75c2f79d9dae1
3
  size 197665365
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7aab10893dabd8225fa97daf0f866c70718a323409d5ac8e474c5b14f073a5
3
  size 197665365