Hugging Face's logo

duyhngoc
/
Wave2Vec2_OV_Vie

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
vivos
Generated from Trainer
Inference Endpoints
Model card Files Community
2
duyhngoc commited on
Commit
c93187e
•
1 Parent(s): e6ea922

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +130 -0
README.md ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - vivos
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: Wave2Vec2_OV_Vie
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: vivos
17
+ type: vivos
18
+ config: default
19
+ split: test
20
+ args: default
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 1.0
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # Wave2Vec2_OV_Vie
31
+
32
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the vivos dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 3.5908
35
+ - Wer: 1.0
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 0.0003
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 2
59
+ - total_train_batch_size: 32
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_steps: 500
63
+ - num_epochs: 15.0
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-----:|:----:|:---------------:|:---:|
69
+ | No log | 0.27 | 100 | 3.9210 | 1.0 |
70
+ | No log | 0.55 | 200 | 3.4375 | 1.0 |
71
+ | No log | 0.82 | 300 | 3.4356 | 1.0 |
72
+ | No log | 1.1 | 400 | 3.4045 | 1.0 |
73
+ | 4.1866 | 1.37 | 500 | 3.4694 | 1.0 |
74
+ | 4.1866 | 1.65 | 600 | 3.6266 | 1.0 |
75
+ | 4.1866 | 1.92 | 700 | 3.5694 | 1.0 |
76
+ | 4.1866 | 2.19 | 800 | 3.5733 | 1.0 |
77
+ | 4.1866 | 2.47 | 900 | 3.6381 | 1.0 |
78
+ | 3.4376 | 2.74 | 1000 | 3.6604 | 1.0 |
79
+ | 3.4376 | 3.02 | 1100 | 3.5868 | 1.0 |
80
+ | 3.4376 | 3.29 | 1200 | 3.4988 | 1.0 |
81
+ | 3.4376 | 3.57 | 1300 | 3.5409 | 1.0 |
82
+ | 3.4376 | 3.84 | 1400 | 3.4883 | 1.0 |
83
+ | 3.4365 | 4.12 | 1500 | 3.6125 | 1.0 |
84
+ | 3.4365 | 4.39 | 1600 | 3.6123 | 1.0 |
85
+ | 3.4365 | 4.66 | 1700 | 3.5978 | 1.0 |
86
+ | 3.4365 | 4.94 | 1800 | 3.5693 | 1.0 |
87
+ | 3.4365 | 5.21 | 1900 | 3.5659 | 1.0 |
88
+ | 3.4339 | 5.49 | 2000 | 3.6234 | 1.0 |
89
+ | 3.4339 | 5.76 | 2100 | 3.5997 | 1.0 |
90
+ | 3.4339 | 6.04 | 2200 | 3.6529 | 1.0 |
91
+ | 3.4339 | 6.31 | 2300 | 3.5780 | 1.0 |
92
+ | 3.4339 | 6.58 | 2400 | 3.5844 | 1.0 |
93
+ | 3.4333 | 6.86 | 2500 | 3.5792 | 1.0 |
94
+ | 3.4333 | 7.13 | 2600 | 3.5468 | 1.0 |
95
+ | 3.4333 | 7.41 | 2700 | 3.5691 | 1.0 |
96
+ | 3.4333 | 7.68 | 2800 | 3.5408 | 1.0 |
97
+ | 3.4333 | 7.96 | 2900 | 3.5482 | 1.0 |
98
+ | 3.4294 | 8.23 | 3000 | 3.6070 | 1.0 |
99
+ | 3.4294 | 8.5 | 3100 | 3.5905 | 1.0 |
100
+ | 3.4294 | 8.78 | 3200 | 3.6018 | 1.0 |
101
+ | 3.4294 | 9.05 | 3300 | 3.6326 | 1.0 |
102
+ | 3.4294 | 9.33 | 3400 | 3.6214 | 1.0 |
103
+ | 3.4293 | 9.6 | 3500 | 3.6372 | 1.0 |
104
+ | 3.4293 | 9.88 | 3600 | 3.6215 | 1.0 |
105
+ | 3.4293 | 10.15 | 3700 | 3.5106 | 1.0 |
106
+ | 3.4293 | 10.43 | 3800 | 3.5066 | 1.0 |
107
+ | 3.4293 | 10.7 | 3900 | 3.5352 | 1.0 |
108
+ | 3.4295 | 10.97 | 4000 | 3.5129 | 1.0 |
109
+ | 3.4295 | 11.25 | 4100 | 3.6384 | 1.0 |
110
+ | 3.4295 | 11.52 | 4200 | 3.6019 | 1.0 |
111
+ | 3.4295 | 11.8 | 4300 | 3.5876 | 1.0 |
112
+ | 3.4295 | 12.07 | 4400 | 3.6207 | 1.0 |
113
+ | 3.4252 | 12.35 | 4500 | 3.5998 | 1.0 |
114
+ | 3.4252 | 12.62 | 4600 | 3.6216 | 1.0 |
115
+ | 3.4252 | 12.89 | 4700 | 3.6073 | 1.0 |
116
+ | 3.4252 | 13.17 | 4800 | 3.5567 | 1.0 |
117
+ | 3.4252 | 13.44 | 4900 | 3.5745 | 1.0 |
118
+ | 3.4274 | 13.72 | 5000 | 3.5738 | 1.0 |
119
+ | 3.4274 | 13.99 | 5100 | 3.5914 | 1.0 |
120
+ | 3.4274 | 14.27 | 5200 | 3.6004 | 1.0 |
121
+ | 3.4274 | 14.54 | 5300 | 3.5968 | 1.0 |
122
+ | 3.4274 | 14.81 | 5400 | 3.5908 | 1.0 |
123
+
124
+
125
+ ### Framework versions
126
+
127
+ - Transformers 4.30.2
128
+ - Pytorch 2.0.1+cu117
129
+ - Datasets 2.13.0
130
+ - Tokenizers 0.13.3