Hugging Face's logo

tuanmanh28
/
wav2vec2-base-vietnamese-VIVOS-CommonVoice-FOSD-Control-dataset-25e-epochs

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
tuanmanh28 commited on
Commit
ef5dc6c
•
1 Parent(s): b51d24a

End of training

Browse files
Files changed (2) hide show
  1. README.md +124 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-VIVOS-CommonVoice-FOSD-Control-dataset-25e-epochs
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-VIVOS-CommonVoice-FOSD-Control-dataset-25e-epochs
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: 0.3338
21
+ - Wer: 0.1833
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: 32
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: 25
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
53
+ | 16.1039 | 0.39 | 500 | 21.1164 | 1.0 |
54
+ | 10.5383 | 0.77 | 1000 | 15.8037 | 1.0 |
55
+ | 7.5435 | 1.16 | 1500 | 9.8785 | 1.0 |
56
+ | 5.1426 | 1.55 | 2000 | 5.9691 | 1.0 |
57
+ | 3.9112 | 1.93 | 2500 | 4.1400 | 1.0 |
58
+ | 3.5159 | 2.32 | 3000 | 3.6877 | 1.0 |
59
+ | 3.4056 | 2.71 | 3500 | 3.5166 | 1.0 |
60
+ | 3.384 | 3.09 | 4000 | 3.6170 | 1.0 |
61
+ | 3.3715 | 3.48 | 4500 | 3.5045 | 1.0 |
62
+ | 3.373 | 3.87 | 5000 | 3.4859 | 1.0 |
63
+ | 3.3539 | 4.25 | 5500 | 3.4843 | 1.0 |
64
+ | 3.3063 | 4.64 | 6000 | 3.3596 | 1.0 |
65
+ | 3.0749 | 5.03 | 6500 | 2.8515 | 0.9994 |
66
+ | 2.6888 | 5.41 | 7000 | 2.4817 | 1.0000 |
67
+ | 2.3404 | 5.8 | 7500 | 2.0490 | 0.9815 |
68
+ | 2.0588 | 6.19 | 8000 | 1.7986 | 0.9288 |
69
+ | 1.8428 | 6.57 | 8500 | 1.4945 | 0.8332 |
70
+ | 1.686 | 6.96 | 9000 | 1.3796 | 0.7640 |
71
+ | 1.5399 | 7.35 | 9500 | 1.2362 | 0.6927 |
72
+ | 1.4374 | 7.73 | 10000 | 1.1130 | 0.6320 |
73
+ | 1.3281 | 8.12 | 10500 | 1.0058 | 0.5705 |
74
+ | 1.2308 | 8.51 | 11000 | 0.8888 | 0.5109 |
75
+ | 1.1405 | 8.89 | 11500 | 0.8438 | 0.4524 |
76
+ | 1.0647 | 9.28 | 12000 | 0.7767 | 0.4208 |
77
+ | 1.0104 | 9.67 | 12500 | 0.7385 | 0.3777 |
78
+ | 0.9629 | 10.05 | 13000 | 0.6731 | 0.3505 |
79
+ | 0.9045 | 10.44 | 13500 | 0.6295 | 0.3317 |
80
+ | 0.8573 | 10.83 | 14000 | 0.6071 | 0.3115 |
81
+ | 0.8443 | 11.21 | 14500 | 0.5895 | 0.2984 |
82
+ | 0.7915 | 11.6 | 15000 | 0.5828 | 0.2823 |
83
+ | 0.7965 | 11.99 | 15500 | 0.5552 | 0.2714 |
84
+ | 0.7738 | 12.37 | 16000 | 0.5100 | 0.2605 |
85
+ | 0.7326 | 12.76 | 16500 | 0.4884 | 0.2499 |
86
+ | 0.7007 | 13.15 | 17000 | 0.4799 | 0.2402 |
87
+ | 0.6997 | 13.53 | 17500 | 0.4647 | 0.2331 |
88
+ | 0.68 | 13.92 | 18000 | 0.4469 | 0.2271 |
89
+ | 0.6707 | 14.31 | 18500 | 0.4261 | 0.2231 |
90
+ | 0.6557 | 14.69 | 19000 | 0.4145 | 0.2164 |
91
+ | 0.6509 | 15.08 | 19500 | 0.4010 | 0.2120 |
92
+ | 0.6649 | 15.47 | 20000 | 0.4038 | 0.2092 |
93
+ | 0.6191 | 15.85 | 20500 | 0.3926 | 0.2064 |
94
+ | 0.6385 | 16.24 | 21000 | 0.3882 | 0.2024 |
95
+ | 0.6222 | 16.63 | 21500 | 0.3874 | 0.2016 |
96
+ | 0.5792 | 17.01 | 22000 | 0.3873 | 0.2023 |
97
+ | 0.5775 | 17.4 | 22500 | 0.3757 | 0.1975 |
98
+ | 0.5647 | 17.79 | 23000 | 0.3626 | 0.1964 |
99
+ | 0.5723 | 18.17 | 23500 | 0.3574 | 0.1958 |
100
+ | 0.5573 | 18.56 | 24000 | 0.3530 | 0.1960 |
101
+ | 0.5813 | 18.95 | 24500 | 0.3541 | 0.1933 |
102
+ | 0.563 | 19.33 | 25000 | 0.3455 | 0.1926 |
103
+ | 0.5402 | 19.72 | 25500 | 0.3483 | 0.1910 |
104
+ | 0.5578 | 20.11 | 26000 | 0.3516 | 0.1915 |
105
+ | 0.5456 | 20.49 | 26500 | 0.3477 | 0.1878 |
106
+ | 0.5453 | 20.88 | 27000 | 0.3391 | 0.1882 |
107
+ | 0.5265 | 21.27 | 27500 | 0.3386 | 0.1869 |
108
+ | 0.557 | 21.66 | 28000 | 0.3388 | 0.1864 |
109
+ | 0.5526 | 22.04 | 28500 | 0.3373 | 0.1864 |
110
+ | 0.5284 | 22.43 | 29000 | 0.3352 | 0.1854 |
111
+ | 0.5351 | 22.82 | 29500 | 0.3373 | 0.1850 |
112
+ | 0.5775 | 23.2 | 30000 | 0.3382 | 0.1848 |
113
+ | 0.5292 | 23.59 | 30500 | 0.3371 | 0.1843 |
114
+ | 0.52 | 23.98 | 31000 | 0.3338 | 0.1839 |
115
+ | 0.5372 | 24.36 | 31500 | 0.3337 | 0.1829 |
116
+ | 0.5167 | 24.75 | 32000 | 0.3338 | 0.1833 |
117
+
118
+
119
+ ### Framework versions
120
+
121
+ - Transformers 4.32.1
122
+ - Pytorch 2.0.1+cu117
123
+ - Datasets 2.14.4
124
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:377273e7713311919bd0251cb178d3b32ef1d06ead41dcfe064d5f7366a8aed9
3
  size 377855649
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01fa4533ece2ec531a872bd914a38a2217d2b145638375a26be3a7ce6147cdf
3
  size 377855649