Hugging Face's logo

sudheer997
/
final-project

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
sudheer997 commited on
Commit
655ebef
·
1 Parent(s): c2c9422

Create 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: uaspeech-foundation-fintuned
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
+ # uaspeech-foundation-fintuned
13
+
14
+ It achieves the following results on the evaluation set:
15
+ - Loss: 2.5324
16
+ - Wer: 1.2855
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0001
36
+ - train_batch_size: 4
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - lr_scheduler_warmup_steps: 1000
42
+ - num_epochs: 30
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
47
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
48
+ | 41.2984 | 0.7 | 500 | 2.8954 | 1.0 |
49
+ | 3.0227 | 1.4 | 1000 | 2.8232 | 1.0042 |
50
+ | 2.8283 | 2.11 | 1500 | 2.6291 | 1.0309 |
51
+ | 2.5552 | 2.81 | 2000 | 2.2593 | 1.9170 |
52
+ | 2.1714 | 3.51 | 2500 | 1.9586 | 1.9142 |
53
+ | 1.8537 | 4.21 | 3000 | 1.5725 | 1.8579 |
54
+ | 1.6087 | 4.92 | 3500 | 1.2772 | 1.7426 |
55
+ | 1.3108 | 5.62 | 4000 | 1.2792 | 1.6751 |
56
+ | 1.1652 | 6.32 | 4500 | 1.4565 | 1.6174 |
57
+ | 1.0113 | 7.02 | 5000 | 1.1906 | 1.5626 |
58
+ | 0.925 | 7.72 | 5500 | 1.4491 | 1.5260 |
59
+ | 0.8183 | 8.43 | 6000 | 1.3712 | 1.5387 |
60
+ | 0.7118 | 9.13 | 6500 | 1.4713 | 1.4866 |
61
+ | 0.6959 | 9.83 | 7000 | 1.3336 | 1.4318 |
62
+ | 0.6146 | 10.53 | 7500 | 1.3690 | 1.4177 |
63
+ | 0.5655 | 11.24 | 8000 | 1.3789 | 1.4135 |
64
+ | 0.4969 | 11.94 | 8500 | 1.5476 | 1.3966 |
65
+ | 0.4705 | 12.64 | 9000 | 1.9062 | 1.3797 |
66
+ | 0.4387 | 13.34 | 9500 | 1.2711 | 1.3924 |
67
+ | 0.4115 | 14.04 | 10000 | 1.6318 | 1.3769 |
68
+ | 0.3695 | 14.75 | 10500 | 1.5119 | 1.3755 |
69
+ | 0.377 | 15.45 | 11000 | 1.6637 | 1.3812 |
70
+ | 0.3788 | 16.15 | 11500 | 1.6636 | 1.3699 |
71
+ | 0.3396 | 16.85 | 12000 | 1.6572 | 1.3418 |
72
+ | 0.3047 | 17.56 | 12500 | 1.4740 | 1.3361 |
73
+ | 0.2804 | 18.26 | 13000 | 2.0885 | 1.3249 |
74
+ | 0.2995 | 18.96 | 13500 | 1.9536 | 1.3235 |
75
+ | 0.2628 | 19.66 | 14000 | 1.7736 | 1.3179 |
76
+ | 0.2703 | 20.37 | 14500 | 2.0018 | 1.3291 |
77
+ | 0.2335 | 21.07 | 15000 | 1.7962 | 1.3221 |
78
+ | 0.2068 | 21.77 | 15500 | 2.3187 | 1.3136 |
79
+ | 0.2311 | 22.47 | 16000 | 2.4853 | 1.3291 |
80
+ | 0.2491 | 23.17 | 16500 | 2.1901 | 1.3024 |
81
+ | 0.1836 | 23.88 | 17000 | 2.4344 | 1.2911 |
82
+ | 0.1823 | 24.58 | 17500 | 2.3705 | 1.3066 |
83
+ | 0.1575 | 25.28 | 18000 | 2.1864 | 1.2897 |
84
+ | 0.1451 | 25.98 | 18500 | 2.4216 | 1.2883 |
85
+ | 0.1502 | 26.69 | 19000 | 2.1780 | 1.2855 |
86
+ | 0.1392 | 27.39 | 19500 | 2.4009 | 1.2925 |
87
+ | 0.1609 | 28.09 | 20000 | 2.4250 | 1.2982 |
88
+ | 0.1066 | 28.79 | 20500 | 2.4433 | 1.2897 |
89
+ | 0.1514 | 29.49 | 21000 | 2.5063 | 1.2855 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.23.1
95
+ - Pytorch 1.12.1+cu113
96
+ - Datasets 1.18.3
97
+ - Tokenizers 0.13.2