Hugging Face's logo

TheAIchemist13
/
hindi_wav2vec2_optimized

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
Community
1
TheAIchemist13 commited on
Commit
004bee8
·
1 Parent(s): 22324a5

End of training

Browse files
Files changed (1) hide show
  1. README.md +51 -16
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: mit
3
- base_model: Harveenchadha/vakyansh-wav2vec2-hindi-him-4200
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # hindi_wav2vec2_optimized
17
 
18
- This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-hindi-him-4200](https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-hindi-him-4200) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.8584
21
- - Wer: 0.2694
22
 
23
  ## Model description
24
 
@@ -45,23 +45,58 @@ The following hyperparameters were used during training:
45
  - total_train_batch_size: 32
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 10
49
- - num_epochs: 125
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
- | 0.1231 | 10.0 | 25 | 1.0084 | 0.3378 |
56
- | 0.0401 | 20.0 | 50 | 1.1598 | 0.3220 |
57
- | 0.0638 | 30.0 | 75 | 1.0830 | 0.3363 |
58
- | 0.0276 | 40.0 | 100 | 0.8550 | 0.3078 |
59
- | 0.0363 | 50.0 | 125 | 0.9201 | 0.3062 |
60
- | 0.0234 | 60.0 | 150 | 0.9475 | 0.2889 |
61
- | 0.024 | 70.0 | 175 | 0.8795 | 0.3123 |
62
- | 0.0151 | 80.0 | 200 | 0.8775 | 0.3017 |
63
- | 0.015 | 90.0 | 225 | 0.8812 | 0.2814 |
64
- | 0.0106 | 100.0 | 250 | 0.8584 | 0.2694 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: TheAIchemist13/hindi_beekeeping_wav2vec2
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # hindi_wav2vec2_optimized
17
 
18
+ This model is a fine-tuned version of [TheAIchemist13/hindi_beekeeping_wav2vec2](https://huggingface.co/TheAIchemist13/hindi_beekeeping_wav2vec2) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6848
21
+ - Wer: 0.4059
22
 
23
  ## Model description
24
 
 
45
  - total_train_batch_size: 32
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 100
49
+ - num_epochs: 5
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 0.312 | 0.11 | 25 | 0.7359 | 0.4045 |
56
+ | 0.2789 | 0.22 | 50 | 0.7344 | 0.4129 |
57
+ | 0.3066 | 0.33 | 75 | 0.7687 | 0.4185 |
58
+ | 0.446 | 0.44 | 100 | 0.9725 | 0.4731 |
59
+ | 0.4249 | 0.54 | 125 | 1.2325 | 0.5073 |
60
+ | 1.2771 | 0.65 | 150 | 1.1657 | 0.5297 |
61
+ | 0.4671 | 0.76 | 175 | 0.9309 | 0.4759 |
62
+ | 0.759 | 0.87 | 200 | 1.0748 | 0.5038 |
63
+ | 0.4854 | 0.98 | 225 | 0.9735 | 0.4990 |
64
+ | 0.4588 | 1.09 | 250 | 0.8566 | 0.4717 |
65
+ | 1.429 | 1.2 | 275 | 0.8819 | 0.5073 |
66
+ | 0.495 | 1.31 | 300 | 0.8920 | 0.4710 |
67
+ | 0.3768 | 1.42 | 325 | 0.9280 | 0.4885 |
68
+ | 0.4792 | 1.53 | 350 | 0.9338 | 0.4689 |
69
+ | 0.4219 | 1.63 | 375 | 1.0726 | 0.5017 |
70
+ | 0.4818 | 1.74 | 400 | 0.9469 | 0.4913 |
71
+ | 0.4148 | 1.85 | 425 | 0.9698 | 0.5108 |
72
+ | 0.5901 | 1.96 | 450 | 0.9540 | 0.5129 |
73
+ | 0.4976 | 2.07 | 475 | 1.0502 | 0.5395 |
74
+ | 0.5696 | 2.18 | 500 | 0.8864 | 0.4675 |
75
+ | 0.4342 | 2.29 | 525 | 0.8964 | 0.4661 |
76
+ | 0.3418 | 2.4 | 550 | 0.9535 | 0.4941 |
77
+ | 0.5812 | 2.51 | 575 | 0.8451 | 0.4514 |
78
+ | 0.3522 | 2.61 | 600 | 0.9054 | 0.4864 |
79
+ | 0.4135 | 2.72 | 625 | 0.8788 | 0.4493 |
80
+ | 0.3061 | 2.83 | 650 | 0.8583 | 0.4570 |
81
+ | 0.4118 | 2.94 | 675 | 0.8105 | 0.4605 |
82
+ | 0.3642 | 3.05 | 700 | 0.8026 | 0.4409 |
83
+ | 0.2803 | 3.16 | 725 | 0.8131 | 0.4297 |
84
+ | 0.3533 | 3.27 | 750 | 0.7614 | 0.4346 |
85
+ | 0.2616 | 3.38 | 775 | 0.8177 | 0.4535 |
86
+ | 0.3203 | 3.49 | 800 | 0.7776 | 0.4409 |
87
+ | 0.2572 | 3.59 | 825 | 0.7438 | 0.4206 |
88
+ | 0.312 | 3.7 | 850 | 0.7454 | 0.4143 |
89
+ | 0.2338 | 3.81 | 875 | 0.7815 | 0.4192 |
90
+ | 0.2921 | 3.92 | 900 | 0.7109 | 0.4122 |
91
+ | 0.2568 | 4.03 | 925 | 0.7430 | 0.4157 |
92
+ | 0.1986 | 4.14 | 950 | 0.7301 | 0.4101 |
93
+ | 0.2569 | 4.25 | 975 | 0.7449 | 0.4150 |
94
+ | 0.1871 | 4.36 | 1000 | 0.7674 | 0.4108 |
95
+ | 0.2449 | 4.47 | 1025 | 0.7218 | 0.4080 |
96
+ | 0.1846 | 4.58 | 1050 | 0.7219 | 0.3933 |
97
+ | 0.2327 | 4.68 | 1075 | 0.7094 | 0.4080 |
98
+ | 0.1921 | 4.79 | 1100 | 0.6858 | 0.4031 |
99
+ | 0.2246 | 4.9 | 1125 | 0.6848 | 0.4059 |
100
 
101
 
102
  ### Framework versions