Hugging Face's logo

rossevine
/
Model_ALL_Wav2Vec2

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
rossevine commited on
Commit
c73b812
•
1 Parent(s): 7884158

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +105 -0
README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - wer
6
+ model-index:
7
+ - name: Model_ALL_Wav2Vec2
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # Model_ALL_Wav2Vec2
15
+
16
+ This model was trained from scratch on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.7779
19
+ - Wer: 0.1975
20
+ - Cer: 0.0813
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0003
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 32
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 30
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
54
+ | 0.8385 | 0.67 | 400 | 0.5656 | 0.3049 | 0.1100 |
55
+ | 0.3291 | 1.34 | 800 | 0.5395 | 0.3184 | 0.1128 |
56
+ | 0.258 | 2.01 | 1200 | 0.4904 | 0.2770 | 0.1030 |
57
+ | 0.217 | 2.68 | 1600 | 0.4673 | 0.2814 | 0.1073 |
58
+ | 0.1956 | 3.35 | 2000 | 0.5108 | 0.2697 | 0.1021 |
59
+ | 0.1872 | 4.02 | 2400 | 0.5531 | 0.2735 | 0.1050 |
60
+ | 0.168 | 4.69 | 2800 | 0.5113 | 0.2536 | 0.0967 |
61
+ | 0.1476 | 5.36 | 3200 | 0.6744 | 0.2420 | 0.0941 |
62
+ | 0.1531 | 6.04 | 3600 | 0.6433 | 0.2492 | 0.0962 |
63
+ | 0.1271 | 6.71 | 4000 | 0.5360 | 0.2392 | 0.0928 |
64
+ | 0.1362 | 7.38 | 4400 | 0.5451 | 0.2458 | 0.0958 |
65
+ | 0.1169 | 8.05 | 4800 | 0.6710 | 0.2470 | 0.0965 |
66
+ | 0.117 | 8.72 | 5200 | 0.5291 | 0.2480 | 0.0990 |
67
+ | 0.1146 | 9.39 | 5600 | 0.6168 | 0.2372 | 0.0927 |
68
+ | 0.1028 | 10.06 | 6000 | 0.5437 | 0.2294 | 0.0914 |
69
+ | 0.0918 | 10.73 | 6400 | 0.6350 | 0.2392 | 0.0947 |
70
+ | 0.1037 | 11.4 | 6800 | 0.6351 | 0.2346 | 0.0920 |
71
+ | 0.0926 | 12.07 | 7200 | 0.6677 | 0.2316 | 0.0924 |
72
+ | 0.0861 | 12.74 | 7600 | 0.5842 | 0.2301 | 0.0934 |
73
+ | 0.0791 | 13.41 | 8000 | 0.5862 | 0.2286 | 0.0916 |
74
+ | 0.08 | 14.08 | 8400 | 0.6183 | 0.2227 | 0.0900 |
75
+ | 0.0707 | 14.75 | 8800 | 0.5985 | 0.2351 | 0.0955 |
76
+ | 0.0719 | 15.42 | 9200 | 0.6327 | 0.2200 | 0.0897 |
77
+ | 0.0674 | 16.09 | 9600 | 0.6184 | 0.2193 | 0.0889 |
78
+ | 0.0612 | 16.76 | 10000 | 0.5501 | 0.2224 | 0.0912 |
79
+ | 0.0607 | 17.44 | 10400 | 0.5404 | 0.2233 | 0.0916 |
80
+ | 0.0612 | 18.11 | 10800 | 0.6111 | 0.2193 | 0.0889 |
81
+ | 0.0542 | 18.78 | 11200 | 0.6610 | 0.2196 | 0.0893 |
82
+ | 0.0517 | 19.45 | 11600 | 0.6083 | 0.2199 | 0.0905 |
83
+ | 0.0478 | 20.12 | 12000 | 0.6500 | 0.2130 | 0.0874 |
84
+ | 0.0464 | 20.79 | 12400 | 0.6671 | 0.2144 | 0.0863 |
85
+ | 0.0395 | 21.46 | 12800 | 0.7239 | 0.2113 | 0.0864 |
86
+ | 0.0391 | 22.13 | 13200 | 0.7791 | 0.2084 | 0.0851 |
87
+ | 0.0362 | 22.8 | 13600 | 0.6682 | 0.2083 | 0.0855 |
88
+ | 0.0396 | 23.47 | 14000 | 0.6608 | 0.2065 | 0.0848 |
89
+ | 0.0346 | 24.14 | 14400 | 0.7438 | 0.2065 | 0.0856 |
90
+ | 0.0368 | 24.81 | 14800 | 0.7382 | 0.2066 | 0.0842 |
91
+ | 0.0273 | 25.48 | 15200 | 0.7486 | 0.2020 | 0.0841 |
92
+ | 0.0286 | 26.15 | 15600 | 0.7566 | 0.2029 | 0.0838 |
93
+ | 0.0268 | 26.82 | 16000 | 0.7680 | 0.2015 | 0.0828 |
94
+ | 0.0248 | 27.49 | 16400 | 0.7499 | 0.1994 | 0.0813 |
95
+ | 0.0253 | 28.16 | 16800 | 0.7511 | 0.1998 | 0.0820 |
96
+ | 0.0228 | 28.83 | 17200 | 0.7686 | 0.1985 | 0.0820 |
97
+ | 0.0212 | 29.51 | 17600 | 0.7779 | 0.1975 | 0.0813 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.31.0
103
+ - Pytorch 2.0.1+cu117
104
+ - Datasets 1.18.3
105
+ - Tokenizers 0.13.3