Hugging Face's logo

thanhduycao
/
wav2vec2-baseline

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
quocanh34/asr_spoken_norm_train_data
Generated from Trainer
Inference Endpoints
Model card Files Community
thanhduycao commited on
Commit
711daf1
•
1 Parent(s): fc336c0

Model save

Browse files
Files changed (1) hide show
  1. README.md +130 -0
README.md ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-baseline
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-baseline
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: nan
21
+ - Wer: 1.0
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: 8e-06
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: 500
47
+ - num_epochs: 30.0
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | No log | 0.43 | 100 | inf | 1.2580 |
54
+ | No log | 0.85 | 200 | inf | 1.0 |
55
+ | No log | 1.28 | 300 | inf | 1.0 |
56
+ | No log | 1.71 | 400 | inf | 1.0 |
57
+ | 12.36 | 2.14 | 500 | inf | 1.0 |
58
+ | 12.36 | 2.56 | 600 | inf | 1.0 |
59
+ | 12.36 | 2.99 | 700 | inf | 1.0 |
60
+ | 12.36 | 3.42 | 800 | inf | 1.0 |
61
+ | 12.36 | 3.85 | 900 | inf | 1.0 |
62
+ | 8.4674 | 4.27 | 1000 | inf | 1.0 |
63
+ | 8.4674 | 4.7 | 1100 | inf | 1.0 |
64
+ | 8.4674 | 5.13 | 1200 | inf | 1.0 |
65
+ | 8.4674 | 5.56 | 1300 | inf | 1.0 |
66
+ | 8.4674 | 5.98 | 1400 | inf | 1.0 |
67
+ | 6.9866 | 6.41 | 1500 | inf | 1.0 |
68
+ | 6.9866 | 6.84 | 1600 | inf | 1.0 |
69
+ | 6.9866 | 7.26 | 1700 | inf | 1.0 |
70
+ | 6.9866 | 7.69 | 1800 | inf | 1.0 |
71
+ | 6.9866 | 8.12 | 1900 | inf | 1.0 |
72
+ | 6.8089 | 8.55 | 2000 | inf | 1.0 |
73
+ | 6.8089 | 8.97 | 2100 | inf | 1.0 |
74
+ | 6.8089 | 9.4 | 2200 | inf | 1.0 |
75
+ | 6.8089 | 9.83 | 2300 | inf | 1.0 |
76
+ | 6.8089 | 10.26 | 2400 | inf | 1.0 |
77
+ | 6.7847 | 10.68 | 2500 | inf | 1.0 |
78
+ | 6.7847 | 11.11 | 2600 | inf | 1.0 |
79
+ | 6.7847 | 11.54 | 2700 | inf | 1.0 |
80
+ | 6.7847 | 11.97 | 2800 | inf | 1.0 |
81
+ | 6.7847 | 12.39 | 2900 | inf | 1.0 |
82
+ | 6.7941 | 12.82 | 3000 | inf | 1.0 |
83
+ | 6.7941 | 13.25 | 3100 | inf | 1.0 |
84
+ | 6.7941 | 13.68 | 3200 | inf | 1.0 |
85
+ | 6.7941 | 14.1 | 3300 | inf | 1.0 |
86
+ | 6.7941 | 14.53 | 3400 | inf | 1.0 |
87
+ | 6.7956 | 14.96 | 3500 | inf | 1.0 |
88
+ | 6.7956 | 15.38 | 3600 | inf | 1.0 |
89
+ | 6.7956 | 15.81 | 3700 | inf | 1.0 |
90
+ | 6.7956 | 16.24 | 3800 | inf | 1.0 |
91
+ | 6.7956 | 16.67 | 3900 | inf | 1.0 |
92
+ | 6.8102 | 17.09 | 4000 | inf | 1.0 |
93
+ | 6.8102 | 17.52 | 4100 | inf | 1.0 |
94
+ | 6.8102 | 17.95 | 4200 | inf | 1.0 |
95
+ | 6.8102 | 18.38 | 4300 | inf | 1.0 |
96
+ | 6.8102 | 18.8 | 4400 | inf | 1.0 |
97
+ | 6.7761 | 19.23 | 4500 | inf | 1.0 |
98
+ | 6.7761 | 19.66 | 4600 | inf | 1.0 |
99
+ | 6.7761 | 20.09 | 4700 | inf | 1.0 |
100
+ | 6.7761 | 20.51 | 4800 | inf | 1.0 |
101
+ | 6.7761 | 20.94 | 4900 | inf | 1.0 |
102
+ | 6.8063 | 21.37 | 5000 | inf | 1.0 |
103
+ | 6.8063 | 21.79 | 5100 | inf | 1.0 |
104
+ | 6.8063 | 22.22 | 5200 | inf | 1.0 |
105
+ | 6.8063 | 22.65 | 5300 | inf | 1.0 |
106
+ | 6.8063 | 23.08 | 5400 | inf | 1.0 |
107
+ | 6.7934 | 23.5 | 5500 | inf | 1.0 |
108
+ | 6.7934 | 23.93 | 5600 | inf | 1.0 |
109
+ | 6.7934 | 24.36 | 5700 | inf | 1.0 |
110
+ | 6.7934 | 24.79 | 5800 | inf | 1.0 |
111
+ | 6.7934 | 25.21 | 5900 | inf | 1.0 |
112
+ | 6.7819 | 25.64 | 6000 | inf | 1.0 |
113
+ | 6.7819 | 26.07 | 6100 | inf | 1.0 |
114
+ | 6.7819 | 26.5 | 6200 | inf | 1.0 |
115
+ | 6.7819 | 26.92 | 6300 | inf | 1.0 |
116
+ | 6.7819 | 27.35 | 6400 | inf | 1.0 |
117
+ | 6.8278 | 27.78 | 6500 | inf | 1.0 |
118
+ | 6.8278 | 28.21 | 6600 | inf | 1.0 |
119
+ | 6.8278 | 28.63 | 6700 | inf | 1.0 |
120
+ | 6.8278 | 29.06 | 6800 | nan | 1.0 |
121
+ | 6.8278 | 29.49 | 6900 | nan | 1.0 |
122
+ | 6.7427 | 29.91 | 7000 | nan | 1.0 |
123
+
124
+
125
+ ### Framework versions
126
+
127
+ - Transformers 4.33.0.dev0
128
+ - Pytorch 2.0.0
129
+ - Datasets 2.14.4
130
+ - Tokenizers 0.13.3