Hugging Face's logo

tuanmanh28
/
wav2vec2_base_vietnamese_control_dataset

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
tuanmanh28 commited on
Commit
7ec2d4c
•
1 Parent(s): 4d3f921

End of training

Browse files
Files changed (2) hide show
  1. README.md +108 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: nguyenvulebinh/wav2vec2-base-vi
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2_base_vietnamese_control_dataset
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
+ # wav2vec2_base_vietnamese_control_dataset
17
+
18
+ This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vi](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vi) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0491
21
+ - Wer: 0.2007
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: 1e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 1000
47
+ - num_epochs: 100
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
53
+ | 19.8101 | 2.05 | 500 | 17.9020 | 1.0 |
54
+ | 12.7254 | 4.1 | 1000 | 13.4585 | 1.0 |
55
+ | 8.6927 | 6.15 | 1500 | 8.4217 | 1.0 |
56
+ | 5.6269 | 8.2 | 2000 | 5.1617 | 1.0 |
57
+ | 3.9616 | 10.25 | 2500 | 3.6167 | 1.0 |
58
+ | 3.2881 | 12.3 | 3000 | 3.2056 | 1.0 |
59
+ | 3.1381 | 14.34 | 3500 | 3.1174 | 1.0 |
60
+ | 3.092 | 16.39 | 4000 | 3.1044 | 1.0 |
61
+ | 3.0222 | 18.44 | 4500 | 2.9461 | 1.0 |
62
+ | 2.8394 | 20.49 | 5000 | 2.7133 | 1.0 |
63
+ | 2.6096 | 22.54 | 5500 | 2.3871 | 1.0 |
64
+ | 2.3244 | 24.59 | 6000 | 2.0311 | 1.0 |
65
+ | 1.9785 | 26.64 | 6500 | 1.6117 | 1.0 |
66
+ | 1.6346 | 28.69 | 7000 | 1.2173 | 1.0 |
67
+ | 1.3122 | 30.74 | 7500 | 0.9547 | 1.0 |
68
+ | 1.0927 | 32.79 | 8000 | 0.7738 | 1.0 |
69
+ | 0.9261 | 34.84 | 8500 | 0.6172 | 0.8970 |
70
+ | 0.7336 | 36.89 | 9000 | 0.4357 | 0.3654 |
71
+ | 0.5754 | 38.93 | 9500 | 0.3304 | 0.3071 |
72
+ | 0.4791 | 40.98 | 10000 | 0.2668 | 0.2785 |
73
+ | 0.4212 | 43.03 | 10500 | 0.2240 | 0.2548 |
74
+ | 0.3439 | 45.08 | 11000 | 0.1852 | 0.2329 |
75
+ | 0.3048 | 47.13 | 11500 | 0.1607 | 0.2119 |
76
+ | 0.2684 | 49.18 | 12000 | 0.1376 | 0.2105 |
77
+ | 0.2298 | 51.23 | 12500 | 0.1227 | 0.2071 |
78
+ | 0.2192 | 53.28 | 13000 | 0.1092 | 0.2055 |
79
+ | 0.2063 | 55.33 | 13500 | 0.0990 | 0.2039 |
80
+ | 0.1875 | 57.38 | 14000 | 0.0895 | 0.2039 |
81
+ | 0.1692 | 59.43 | 14500 | 0.0822 | 0.2039 |
82
+ | 0.1421 | 61.48 | 15000 | 0.0766 | 0.2029 |
83
+ | 0.1505 | 63.52 | 15500 | 0.0710 | 0.2031 |
84
+ | 0.1796 | 65.57 | 16000 | 0.0682 | 0.2019 |
85
+ | 0.1265 | 67.62 | 16500 | 0.0641 | 0.2015 |
86
+ | 0.1172 | 69.67 | 17000 | 0.0617 | 0.2019 |
87
+ | 0.1173 | 71.72 | 17500 | 0.0586 | 0.2011 |
88
+ | 0.1226 | 73.77 | 18000 | 0.0568 | 0.2015 |
89
+ | 0.1165 | 75.82 | 18500 | 0.0567 | 0.2011 |
90
+ | 0.1098 | 77.87 | 19000 | 0.0547 | 0.2007 |
91
+ | 0.0996 | 79.92 | 19500 | 0.0537 | 0.2009 |
92
+ | 0.1024 | 81.97 | 20000 | 0.0521 | 0.2009 |
93
+ | 0.0992 | 84.02 | 20500 | 0.0508 | 0.2009 |
94
+ | 0.1008 | 86.07 | 21000 | 0.0510 | 0.2009 |
95
+ | 0.1147 | 88.11 | 21500 | 0.0501 | 0.2007 |
96
+ | 0.1138 | 90.16 | 22000 | 0.0500 | 0.2005 |
97
+ | 0.0939 | 92.21 | 22500 | 0.0493 | 0.2007 |
98
+ | 0.1021 | 94.26 | 23000 | 0.0492 | 0.2005 |
99
+ | 0.1009 | 96.31 | 23500 | 0.0488 | 0.2009 |
100
+ | 0.0935 | 98.36 | 24000 | 0.0491 | 0.2007 |
101
+
102
+
103
+ ### Framework versions
104
+
105
+ - Transformers 4.32.1
106
+ - Pytorch 2.0.1+cu117
107
+ - Datasets 2.14.4
108
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17bf096f3d6c01ef3451b40abc078a369d0552daa30de7a833db93d636cef229
3
  size 377855649
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:714c64fe69a3fb4ffe8b12542f56e2ebe10fb6316d9a58f5da24156b454b03f7
3
  size 377855649