Hugging Face's logo

tuanio
/
fine-w2v2base-bs16-ep100-lr2e-05-linguistic-rmsnorm-focal_ctc_a0.99_g1.0-0.05_10_0.004_40

Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
tuanio commited on
Commit
b263f5c
·
1 Parent(s): 460b4ae

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_a0.99_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_a0.99_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: 4.2488
21
+ - Wer: 0.0990
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
+ | 2181.8592 | 0.94 | 50 | 1087.6210 | 15.9420 |
58
+ | 1908.6856 | 1.89 | 100 | 809.7703 | 15.8773 |
59
+ | 838.4017 | 2.83 | 150 | 112.6467 | 0.9997 |
60
+ | 117.7945 | 3.77 | 200 | 85.6792 | 1.0 |
61
+ | 109.9946 | 4.72 | 250 | 82.5771 | 1.0 |
62
+ | 105.7306 | 5.66 | 300 | 79.6600 | 1.0 |
63
+ | 102.0127 | 6.6 | 350 | 77.2287 | 1.0 |
64
+ | 97.9428 | 7.55 | 400 | 75.4334 | 1.0 |
65
+ | 96.0055 | 8.49 | 450 | 74.6870 | 1.0 |
66
+ | 96.9376 | 9.43 | 500 | 74.2493 | 1.0 |
67
+ | 95.6634 | 10.38 | 550 | 74.1341 | 1.0 |
68
+ | 96.1578 | 11.32 | 600 | 74.9003 | 1.0 |
69
+ | 92.5678 | 12.26 | 650 | 75.6603 | 1.0598 |
70
+ | 90.5927 | 13.21 | 700 | 73.4555 | 1.0539 |
71
+ | 87.8965 | 14.15 | 750 | 72.4102 | 0.9987 |
72
+ | 86.8467 | 15.09 | 800 | 69.7737 | 0.9984 |
73
+ | 85.3381 | 16.04 | 850 | 67.8433 | 0.9717 |
74
+ | 80.3298 | 16.98 | 900 | 52.4081 | 0.8594 |
75
+ | 56.9494 | 17.92 | 950 | 25.2678 | 0.3554 |
76
+ | 32.292 | 18.87 | 1000 | 14.8634 | 0.2190 |
77
+ | 22.3255 | 19.81 | 1050 | 11.2898 | 0.1823 |
78
+ | 17.6187 | 20.75 | 1100 | 9.1387 | 0.1534 |
79
+ | 15.1531 | 21.7 | 1150 | 7.6636 | 0.1368 |
80
+ | 13.1696 | 22.64 | 1200 | 7.0291 | 0.1434 |
81
+ | 11.9792 | 23.58 | 1250 | 6.6867 | 0.1325 |
82
+ | 11.2404 | 24.53 | 1300 | 6.2948 | 0.1213 |
83
+ | 10.6256 | 25.47 | 1350 | 5.7151 | 0.1180 |
84
+ | 9.452 | 26.42 | 1400 | 5.4196 | 0.1175 |
85
+ | 9.3087 | 27.36 | 1450 | 5.2929 | 0.1124 |
86
+ | 8.5149 | 28.3 | 1500 | 5.1394 | 0.1163 |
87
+ | 8.3662 | 29.25 | 1550 | 5.1275 | 0.1213 |
88
+ | 7.8852 | 30.19 | 1600 | 4.9033 | 0.1093 |
89
+ | 7.5135 | 31.13 | 1650 | 4.9572 | 0.1097 |
90
+ | 7.5374 | 32.08 | 1700 | 4.7588 | 0.1016 |
91
+ | 7.2968 | 33.02 | 1750 | 4.7317 | 0.1033 |
92
+ | 7.0861 | 33.96 | 1800 | 4.7916 | 0.1087 |
93
+ | 6.6371 | 34.91 | 1850 | 4.7941 | 0.1132 |
94
+ | 6.6186 | 35.85 | 1900 | 4.6608 | 0.1036 |
95
+ | 6.6288 | 36.79 | 1950 | 4.6790 | 0.1074 |
96
+ | 6.2433 | 37.74 | 2000 | 4.7715 | 0.1121 |
97
+ | 6.2362 | 38.68 | 2050 | 4.6420 | 0.1034 |
98
+ | 5.957 | 39.62 | 2100 | 4.5756 | 0.1070 |
99
+ | 5.8034 | 40.57 | 2150 | 4.4112 | 0.1060 |
100
+ | 5.4943 | 41.51 | 2200 | 4.5632 | 0.1034 |
101
+ | 5.5593 | 42.45 | 2250 | 4.5376 | 0.1105 |
102
+ | 5.3447 | 43.4 | 2300 | 4.5423 | 0.1006 |
103
+ | 5.4181 | 44.34 | 2350 | 4.3789 | 0.0993 |
104
+ | 5.222 | 45.28 | 2400 | 4.3695 | 0.1031 |
105
+ | 5.1146 | 46.23 | 2450 | 4.4108 | 0.1084 |
106
+ | 5.0952 | 47.17 | 2500 | 4.2957 | 0.1016 |
107
+ | 4.9023 | 48.11 | 2550 | 4.3769 | 0.1021 |
108
+ | 5.1633 | 49.06 | 2600 | 4.3633 | 0.1063 |
109
+ | 4.9489 | 50.0 | 2650 | 4.3422 | 0.1045 |
110
+ | 4.7391 | 50.94 | 2700 | 4.2510 | 0.1029 |
111
+ | 4.7996 | 51.89 | 2750 | 4.3254 | 0.1012 |
112
+ | 4.244 | 52.83 | 2800 | 4.4121 | 0.1035 |
113
+ | 4.5831 | 53.77 | 2850 | 4.4056 | 0.1044 |
114
+ | 4.5198 | 54.72 | 2900 | 4.3638 | 0.1050 |
115
+ | 4.1964 | 55.66 | 2950 | 4.3397 | 0.1071 |
116
+ | 4.0544 | 56.6 | 3000 | 4.3493 | 0.1031 |
117
+ | 4.3568 | 57.55 | 3050 | 4.4721 | 0.1059 |
118
+ | 4.2692 | 58.49 | 3100 | 4.4278 | 0.1117 |
119
+ | 4.1226 | 59.43 | 3150 | 4.3081 | 0.1004 |
120
+ | 4.2681 | 60.38 | 3200 | 4.4176 | 0.1059 |
121
+ | 3.8412 | 61.32 | 3250 | 4.3213 | 0.1028 |
122
+ | 4.1387 | 62.26 | 3300 | 4.3419 | 0.1056 |
123
+ | 3.6847 | 63.21 | 3350 | 4.2498 | 0.1065 |
124
+ | 3.8768 | 64.15 | 3400 | 4.2776 | 0.1028 |
125
+ | 3.659 | 65.09 | 3450 | 4.2988 | 0.1008 |
126
+ | 3.809 | 66.04 | 3500 | 4.3041 | 0.1034 |
127
+ | 3.7459 | 66.98 | 3550 | 4.2955 | 0.0995 |
128
+ | 3.7996 | 67.92 | 3600 | 4.2843 | 0.0993 |
129
+ | 3.6773 | 68.87 | 3650 | 4.2396 | 0.0988 |
130
+ | 3.6364 | 69.81 | 3700 | 4.2206 | 0.0963 |
131
+ | 3.6342 | 70.75 | 3750 | 4.2905 | 0.1018 |
132
+ | 3.7012 | 71.7 | 3800 | 4.3084 | 0.0994 |
133
+ | 3.4846 | 72.64 | 3850 | 4.2872 | 0.0976 |
134
+ | 3.4814 | 73.58 | 3900 | 4.2596 | 0.1003 |
135
+ | 3.3212 | 74.53 | 3950 | 4.2270 | 0.0964 |
136
+ | 3.6578 | 75.47 | 4000 | 4.2477 | 0.0978 |
137
+ | 3.4573 | 76.42 | 4050 | 4.2389 | 0.0973 |
138
+ | 3.5776 | 77.36 | 4100 | 4.2827 | 0.0989 |
139
+ | 3.5116 | 78.3 | 4150 | 4.3245 | 0.1002 |
140
+ | 3.3334 | 79.25 | 4200 | 4.2707 | 0.0996 |
141
+ | 3.4829 | 80.19 | 4250 | 4.2456 | 0.0982 |
142
+ | 3.44 | 81.13 | 4300 | 4.2846 | 0.1003 |
143
+ | 3.4112 | 82.08 | 4350 | 4.2800 | 0.0977 |
144
+ | 3.3825 | 83.02 | 4400 | 4.2569 | 0.0976 |
145
+ | 3.3444 | 83.96 | 4450 | 4.2334 | 0.0949 |
146
+ | 3.5125 | 84.91 | 4500 | 4.2632 | 0.0978 |
147
+ | 3.3393 | 85.85 | 4550 | 4.2508 | 0.0979 |
148
+ | 3.4698 | 86.79 | 4600 | 4.2483 | 0.1000 |
149
+ | 3.3466 | 87.74 | 4650 | 4.2560 | 0.0985 |
150
+ | 3.3808 | 88.68 | 4700 | 4.2550 | 0.0973 |
151
+ | 3.3442 | 89.62 | 4750 | 4.2574 | 0.0982 |
152
+ | 3.0359 | 90.57 | 4800 | 4.2572 | 0.0993 |
153
+ | 3.5286 | 91.51 | 4850 | 4.2509 | 0.0993 |
154
+ | 3.0826 | 92.45 | 4900 | 4.2408 | 0.0977 |
155
+ | 3.513 | 93.4 | 4950 | 4.2531 | 0.0990 |
156
+ | 3.272 | 94.34 | 5000 | 4.2558 | 0.0995 |
157
+ | 3.2433 | 95.28 | 5050 | 4.2515 | 0.0992 |
158
+ | 3.3373 | 96.23 | 5100 | 4.2524 | 0.1001 |
159
+ | 3.2239 | 97.17 | 5150 | 4.2540 | 0.0995 |
160
+ | 3.4072 | 98.11 | 5200 | 4.2486 | 0.0993 |
161
+ | 3.3015 | 99.06 | 5250 | 4.2497 | 0.0988 |
162
+ | 3.329 | 100.0 | 5300 | 4.2488 | 0.0990 |
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 sha256:4541184f96a2b3ce261477ff7011eeaa2789d8c9b6dfb9c0a05859e454eb15ab
3
  size 197665365
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c4d3ae3a87b9569e6d35696b7c2fb40e6748c92615cd041ce63031679962b1
3
  size 197665365