Hugging Face's logo

DRAGOO
/
mounir2

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
1
DRAGOO commited on
Commit
78555cd
·
1 Parent(s): 9218957

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +112 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: mounir2
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # mounir2
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8560
20
+ - Wer: 1
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: 1e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 16
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 3000
48
+ - training_steps: 5000
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:---:|
55
+ | 26.8537 | 0.42 | 100 | 25.5127 | 1 |
56
+ | 23.3042 | 0.85 | 200 | 20.5838 | 1 |
57
+ | 13.5844 | 1.27 | 300 | 10.8923 | 1 |
58
+ | 5.8285 | 1.7 | 400 | 4.5743 | 1 |
59
+ | 3.6732 | 2.12 | 500 | 3.4595 | 1 |
60
+ | 3.4969 | 2.55 | 600 | 3.3192 | 1 |
61
+ | 3.7275 | 2.97 | 700 | 3.2367 | 1 |
62
+ | 3.3092 | 3.4 | 800 | 3.1613 | 1 |
63
+ | 3.1658 | 3.82 | 900 | 3.1019 | 1 |
64
+ | 3.1157 | 4.25 | 1000 | 3.0578 | 1 |
65
+ | 3.105 | 4.67 | 1100 | 3.0208 | 1 |
66
+ | 3.0181 | 5.1 | 1200 | 2.9876 | 1 |
67
+ | 3.0154 | 5.52 | 1300 | 2.9543 | 1 |
68
+ | 2.9889 | 5.94 | 1400 | 2.9387 | 1 |
69
+ | 2.9461 | 6.37 | 1500 | 2.9246 | 1 |
70
+ | 2.9261 | 6.79 | 1600 | 2.9111 | 1 |
71
+ | 2.919 | 7.22 | 1700 | 2.9049 | 1 |
72
+ | 2.9235 | 7.64 | 1800 | 2.8974 | 1 |
73
+ | 2.899 | 8.07 | 1900 | 2.8864 | 1 |
74
+ | 2.9122 | 8.49 | 2000 | 2.8994 | 1 |
75
+ | 2.8856 | 8.92 | 2100 | 2.8789 | 1 |
76
+ | 2.8693 | 9.34 | 2200 | 2.8765 | 1 |
77
+ | 2.9063 | 9.77 | 2300 | 2.8693 | 1 |
78
+ | 2.8701 | 10.19 | 2400 | 2.8700 | 1 |
79
+ | 2.9013 | 10.62 | 2500 | 2.8647 | 1 |
80
+ | 2.8715 | 11.04 | 2600 | 2.8605 | 1 |
81
+ | 2.8524 | 11.46 | 2700 | 2.8706 | 1 |
82
+ | 2.8551 | 11.89 | 2800 | 2.8534 | 1 |
83
+ | 2.8466 | 12.31 | 2900 | 2.8517 | 1 |
84
+ | 2.8419 | 12.74 | 3000 | 2.8604 | 1 |
85
+ | 2.8345 | 13.16 | 3100 | 2.8388 | 1 |
86
+ | 2.827 | 13.59 | 3200 | 2.8220 | 1 |
87
+ | 2.6233 | 14.01 | 3300 | 2.5103 | 1 |
88
+ | 2.2908 | 14.44 | 3400 | 2.1460 | 1 |
89
+ | 1.9386 | 14.86 | 3500 | 1.7383 | 1 |
90
+ | 1.6341 | 15.29 | 3600 | 1.4527 | 1 |
91
+ | 1.5684 | 15.71 | 3700 | 1.2669 | 1 |
92
+ | 1.2713 | 16.14 | 3800 | 1.1512 | 1 |
93
+ | 1.1983 | 16.56 | 3900 | 1.0776 | 1 |
94
+ | 1.1806 | 16.99 | 4000 | 1.0261 | 1 |
95
+ | 1.1456 | 17.41 | 4100 | 0.9729 | 1 |
96
+ | 1.0942 | 17.83 | 4200 | 0.9407 | 1 |
97
+ | 1.0452 | 18.26 | 4300 | 0.9172 | 1 |
98
+ | 1.0082 | 18.68 | 4400 | 0.9006 | 1 |
99
+ | 0.9748 | 19.11 | 4500 | 0.8902 | 1 |
100
+ | 0.9672 | 19.53 | 4600 | 0.8742 | 1 |
101
+ | 0.9737 | 19.96 | 4700 | 0.8738 | 1 |
102
+ | 0.9567 | 20.38 | 4800 | 0.8639 | 1 |
103
+ | 0.988 | 20.81 | 4900 | 0.8565 | 1 |
104
+ | 0.9783 | 21.23 | 5000 | 0.8560 | 1 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - Transformers 4.28.0
110
+ - Pytorch 2.0.1+cu117
111
+ - Datasets 2.12.0
112
+ - Tokenizers 0.13.3