Hugging Face's logo

TheAIchemist13
/
hindi_wav2vec2_final

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
Community
1
TheAIchemist13 commited on
Commit
61b465d
·
1 Parent(s): 710ca44

End of training

Browse files
Files changed (2) hide show
  1. README.md +142 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: Harveenchadha/vakyansh-wav2vec2-hindi-him-4200
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: hindi_wav2vec2_final
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # hindi_wav2vec2_final
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: 0.0000
21
+ - Wer: 0.0699
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0003
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
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: 1000
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | No log | 10.0 | 25 | 2.4458 | 0.9376 |
56
+ | No log | 20.0 | 50 | 0.5012 | 0.1820 |
57
+ | No log | 30.0 | 75 | 0.2451 | 0.1511 |
58
+ | No log | 40.0 | 100 | 0.0827 | 0.1211 |
59
+ | No log | 50.0 | 125 | 0.0438 | 0.0902 |
60
+ | No log | 60.0 | 150 | 0.0271 | 0.0827 |
61
+ | No log | 70.0 | 175 | 0.0282 | 0.0759 |
62
+ | No log | 80.0 | 200 | 0.0089 | 0.0677 |
63
+ | No log | 90.0 | 225 | 0.0217 | 0.0752 |
64
+ | No log | 100.0 | 250 | 0.0088 | 0.0609 |
65
+ | No log | 110.0 | 275 | 0.0076 | 0.0947 |
66
+ | No log | 120.0 | 300 | 0.0085 | 0.0624 |
67
+ | No log | 130.0 | 325 | 0.0060 | 0.0632 |
68
+ | No log | 140.0 | 350 | 0.0101 | 0.0654 |
69
+ | No log | 150.0 | 375 | 0.0031 | 0.0579 |
70
+ | No log | 160.0 | 400 | 0.0035 | 0.0624 |
71
+ | No log | 170.0 | 425 | 0.0048 | 0.0744 |
72
+ | No log | 180.0 | 450 | 0.0035 | 0.0744 |
73
+ | No log | 190.0 | 475 | 0.0196 | 0.0707 |
74
+ | 1.3647 | 200.0 | 500 | 0.0036 | 0.0624 |
75
+ | 1.3647 | 210.0 | 525 | 0.0019 | 0.0617 |
76
+ | 1.3647 | 220.0 | 550 | 0.0022 | 0.0714 |
77
+ | 1.3647 | 230.0 | 575 | 0.0020 | 0.0639 |
78
+ | 1.3647 | 240.0 | 600 | 0.0022 | 0.0594 |
79
+ | 1.3647 | 250.0 | 625 | 0.0014 | 0.0857 |
80
+ | 1.3647 | 260.0 | 650 | 0.0053 | 0.0744 |
81
+ | 1.3647 | 270.0 | 675 | 0.0011 | 0.0609 |
82
+ | 1.3647 | 280.0 | 700 | 0.0007 | 0.0602 |
83
+ | 1.3647 | 290.0 | 725 | 0.0034 | 0.0632 |
84
+ | 1.3647 | 300.0 | 750 | 0.0021 | 0.0609 |
85
+ | 1.3647 | 310.0 | 775 | 0.0009 | 0.0624 |
86
+ | 1.3647 | 320.0 | 800 | 0.0025 | 0.0609 |
87
+ | 1.3647 | 330.0 | 825 | 0.0004 | 0.0579 |
88
+ | 1.3647 | 340.0 | 850 | 0.0002 | 0.0594 |
89
+ | 1.3647 | 350.0 | 875 | 0.0002 | 0.0594 |
90
+ | 1.3647 | 360.0 | 900 | 0.0054 | 0.0617 |
91
+ | 1.3647 | 370.0 | 925 | 0.0007 | 0.0602 |
92
+ | 1.3647 | 380.0 | 950 | 0.0005 | 0.0609 |
93
+ | 1.3647 | 390.0 | 975 | 0.0002 | 0.0594 |
94
+ | 0.0095 | 400.0 | 1000 | 0.0005 | 0.0609 |
95
+ | 0.0095 | 410.0 | 1025 | 0.0002 | 0.0609 |
96
+ | 0.0095 | 420.0 | 1050 | 0.0002 | 0.0632 |
97
+ | 0.0095 | 430.0 | 1075 | 0.0003 | 0.0647 |
98
+ | 0.0095 | 440.0 | 1100 | 0.0010 | 0.0617 |
99
+ | 0.0095 | 450.0 | 1125 | 0.0055 | 0.0654 |
100
+ | 0.0095 | 460.0 | 1150 | 0.0002 | 0.0602 |
101
+ | 0.0095 | 470.0 | 1175 | 0.0001 | 0.0602 |
102
+ | 0.0095 | 480.0 | 1200 | 0.0002 | 0.0617 |
103
+ | 0.0095 | 490.0 | 1225 | 0.0001 | 0.0609 |
104
+ | 0.0095 | 500.0 | 1250 | 0.0001 | 0.0624 |
105
+ | 0.0095 | 510.0 | 1275 | 0.0001 | 0.0632 |
106
+ | 0.0095 | 520.0 | 1300 | 0.0001 | 0.0632 |
107
+ | 0.0095 | 530.0 | 1325 | 0.0001 | 0.0669 |
108
+ | 0.0095 | 540.0 | 1350 | 0.0001 | 0.0654 |
109
+ | 0.0095 | 550.0 | 1375 | 0.0001 | 0.0677 |
110
+ | 0.0095 | 560.0 | 1400 | 0.0001 | 0.0632 |
111
+ | 0.0095 | 570.0 | 1425 | 0.0001 | 0.0609 |
112
+ | 0.0095 | 580.0 | 1450 | 0.0001 | 0.0609 |
113
+ | 0.0095 | 590.0 | 1475 | 0.0001 | 0.0632 |
114
+ | 0.0031 | 600.0 | 1500 | 0.0001 | 0.0714 |
115
+ | 0.0031 | 610.0 | 1525 | 0.0001 | 0.0692 |
116
+ | 0.0031 | 620.0 | 1550 | 0.0001 | 0.0707 |
117
+ | 0.0031 | 630.0 | 1575 | 0.0001 | 0.0677 |
118
+ | 0.0031 | 640.0 | 1600 | 0.0001 | 0.0902 |
119
+ | 0.0031 | 650.0 | 1625 | 0.0000 | 0.0714 |
120
+ | 0.0031 | 660.0 | 1650 | 0.0000 | 0.0767 |
121
+ | 0.0031 | 670.0 | 1675 | 0.0000 | 0.0737 |
122
+ | 0.0031 | 680.0 | 1700 | 0.0000 | 0.0669 |
123
+ | 0.0031 | 690.0 | 1725 | 0.0000 | 0.0677 |
124
+ | 0.0031 | 700.0 | 1750 | 0.0000 | 0.0669 |
125
+ | 0.0031 | 710.0 | 1775 | 0.0000 | 0.0684 |
126
+ | 0.0031 | 720.0 | 1800 | 0.0000 | 0.0669 |
127
+ | 0.0031 | 730.0 | 1825 | 0.0000 | 0.0677 |
128
+ | 0.0031 | 740.0 | 1850 | 0.0000 | 0.0647 |
129
+ | 0.0031 | 750.0 | 1875 | 0.0000 | 0.0647 |
130
+ | 0.0031 | 760.0 | 1900 | 0.0000 | 0.0647 |
131
+ | 0.0031 | 770.0 | 1925 | 0.0000 | 0.0699 |
132
+ | 0.0031 | 780.0 | 1950 | 0.0000 | 0.0699 |
133
+ | 0.0031 | 790.0 | 1975 | 0.0000 | 0.0692 |
134
+ | 0.0014 | 800.0 | 2000 | 0.0000 | 0.0699 |
135
+
136
+
137
+ ### Framework versions
138
+
139
+ - Transformers 4.34.0
140
+ - Pytorch 2.0.1+cu118
141
+ - Datasets 1.18.3
142
+ - Tokenizers 0.14.1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a6db7c1f134620ea0237db084b562adbe780c98a78944f79d35728a5edb3e07
3
  size 377766433
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c085a9f9573d1e9e06b1d77f5649183c25bf5fdda713eb774680eff2f665781
3
  size 377766433