Hugging Face's logo

GW12
/
wav2vec2-custom-colab

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
Community
1
GW12 commited on
Commit
c125909
·
1 Parent(s): 5fd23ab

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: wav2vec2-custom-colab
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
+ # wav2vec2-custom-colab
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: 0.7785
20
+ - Wer: 0.3534
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: 0.0001
40
+ - train_batch_size: 1
41
+ - eval_batch_size: 1
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 1000
46
+ - num_epochs: 10
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
53
+ | 0.4783 | 0.3 | 500 | 0.7199 | 0.5564 |
54
+ | 0.4833 | 0.61 | 1000 | 0.8089 | 0.6181 |
55
+ | 0.5733 | 0.91 | 1500 | 0.7617 | 0.5530 |
56
+ | 0.4641 | 1.21 | 2000 | 0.7937 | 0.5731 |
57
+ | 0.4167 | 1.52 | 2500 | 0.7993 | 0.5102 |
58
+ | 0.3713 | 1.82 | 3000 | 0.7541 | 0.5437 |
59
+ | 0.3395 | 2.12 | 3500 | 0.7658 | 0.5148 |
60
+ | 0.2814 | 2.42 | 4000 | 0.7569 | 0.4783 |
61
+ | 0.2698 | 2.73 | 4500 | 0.8126 | 0.5174 |
62
+ | 0.2767 | 3.03 | 5000 | 0.7838 | 0.4676 |
63
+ | 0.2249 | 3.33 | 5500 | 0.8769 | 0.4743 |
64
+ | 0.2452 | 3.64 | 6000 | 0.8586 | 0.4778 |
65
+ | 0.1828 | 3.94 | 6500 | 0.7695 | 0.4528 |
66
+ | 0.1901 | 4.24 | 7000 | 0.7800 | 0.5021 |
67
+ | 0.2062 | 4.55 | 7500 | 0.8107 | 0.4567 |
68
+ | 0.1614 | 4.85 | 8000 | 0.7941 | 0.4094 |
69
+ | 0.1327 | 5.15 | 8500 | 0.7900 | 0.4241 |
70
+ | 0.1405 | 5.45 | 9000 | 0.8017 | 0.3992 |
71
+ | 0.1219 | 5.76 | 9500 | 0.8099 | 0.4043 |
72
+ | 0.1406 | 6.06 | 10000 | 0.8731 | 0.3913 |
73
+ | 0.0806 | 6.36 | 10500 | 0.8387 | 0.3868 |
74
+ | 0.1039 | 6.67 | 11000 | 0.8105 | 0.3905 |
75
+ | 0.0967 | 6.97 | 11500 | 0.7291 | 0.3728 |
76
+ | 0.0846 | 7.27 | 12000 | 0.8128 | 0.4201 |
77
+ | 0.0722 | 7.58 | 12500 | 0.8204 | 0.3751 |
78
+ | 0.0785 | 7.88 | 13000 | 0.7692 | 0.3760 |
79
+ | 0.0647 | 8.18 | 13500 | 0.8294 | 0.3752 |
80
+ | 0.0523 | 8.48 | 14000 | 0.7646 | 0.3763 |
81
+ | 0.0623 | 8.79 | 14500 | 0.7773 | 0.3572 |
82
+ | 0.0477 | 9.09 | 15000 | 0.7379 | 0.3635 |
83
+ | 0.064 | 9.39 | 15500 | 0.7544 | 0.3538 |
84
+ | 0.0321 | 9.7 | 16000 | 0.8118 | 0.3557 |
85
+ | 0.0541 | 10.0 | 16500 | 0.7785 | 0.3534 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.26.0
91
+ - Pytorch 1.10.0
92
+ - Datasets 2.9.0
93
+ - Tokenizers 0.13.2