Hugging Face's logo

modhp
/
wav2vec2-model2-torgo

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files
xet
 Metrics Community
1
modhp commited on
Commit
6f9049b
·
1 Parent(s): df8253c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +97 -0
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: wav2vec2-model2-torgo
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # wav2vec2-model2-torgo
13
+
14
+ This model was trained from scratch on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 4.9975
17
+ - Wer: 1.0
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.1
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 4
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 1000
45
+ - num_epochs: 30
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:---:|
51
+ | 12.5453 | 0.76 | 500 | 14.6490 | 1.0 |
52
+ | 4.8036 | 1.53 | 1000 | 8.4523 | 1.0 |
53
+ | 5.0421 | 2.29 | 1500 | 5.4114 | 1.0 |
54
+ | 5.2055 | 3.05 | 2000 | 11.0507 | 1.0 |
55
+ | 4.6389 | 3.82 | 2500 | 4.6792 | 1.0 |
56
+ | 4.5523 | 4.58 | 3000 | 4.7855 | 1.0 |
57
+ | 4.7843 | 5.34 | 3500 | 11.2783 | 1.0 |
58
+ | 4.6066 | 6.11 | 4000 | 8.7807 | 1.0 |
59
+ | 4.7382 | 6.87 | 4500 | 2942.0220 | 1.0 |
60
+ | 130.5733 | 7.63 | 5000 | 5.8412 | 1.0 |
61
+ | 4.4972 | 8.4 | 5500 | 17.7038 | 1.0 |
62
+ | 4.5196 | 9.16 | 6000 | 11.4548 | 1.0 |
63
+ | 4.3198 | 9.92 | 6500 | 6.0885 | 1.0 |
64
+ | 4.4273 | 10.69 | 7000 | 6.7374 | 1.0 |
65
+ | 4.2783 | 11.45 | 7500 | 4.7276 | 1.0 |
66
+ | 4.2985 | 12.21 | 8000 | 6.1412 | 1.0 |
67
+ | 4.3262 | 12.98 | 8500 | 5.2621 | 1.0 |
68
+ | 4.1705 | 13.74 | 9000 | 5.2214 | 1.0 |
69
+ | 4.3176 | 14.5 | 9500 | 5.5359 | 1.0 |
70
+ | 3.9808 | 15.27 | 10000 | 4.1537 | 1.0 |
71
+ | 4.0228 | 16.03 | 10500 | 4.2962 | 1.0 |
72
+ | 4.0595 | 16.79 | 11000 | 7.6361 | 1.0 |
73
+ | 4.0088 | 17.56 | 11500 | 6.8715 | 1.0 |
74
+ | 3.8727 | 18.32 | 12000 | 8.8657 | 1.0 |
75
+ | 4.0073 | 19.08 | 12500 | 5.8170 | 1.0 |
76
+ | 3.8511 | 19.85 | 13000 | 13.9836 | 1.0 |
77
+ | 4.0899 | 20.61 | 13500 | 5.3287 | 1.0 |
78
+ | 3.8782 | 21.37 | 14000 | 8.0635 | 1.0 |
79
+ | 3.9235 | 22.14 | 14500 | 5.5129 | 1.0 |
80
+ | 3.7276 | 22.9 | 15000 | 5.0819 | 1.0 |
81
+ | 3.7908 | 23.66 | 15500 | 6.1458 | 1.0 |
82
+ | 3.9176 | 24.43 | 16000 | 4.6094 | 1.0 |
83
+ | 3.8477 | 25.19 | 16500 | 5.1406 | 1.0 |
84
+ | 3.6917 | 25.95 | 17000 | 4.5684 | 1.0 |
85
+ | 3.8568 | 26.72 | 17500 | 4.0306 | 1.0 |
86
+ | 3.7231 | 27.48 | 18000 | 5.6331 | 1.0 |
87
+ | 3.8145 | 28.24 | 18500 | 8.2997 | 1.0 |
88
+ | 3.7809 | 29.01 | 19000 | 5.7468 | 1.0 |
89
+ | 3.5995 | 29.77 | 19500 | 4.9975 | 1.0 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.17.0
95
+ - Pytorch 1.11.0
96
+ - Datasets 1.18.3
97
+ - Tokenizers 0.11.6