Hugging Face's logo

Revolt47
/
wav2vec2-urdufinetuned

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Revolt47 commited on
Commit
ad4eea1
•
1 Parent(s): 66b4195

End of training

Browse files
Files changed (1) hide show
  1. README.md +133 -0
README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base-960h
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2-urdufinetuned
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
+ # wav2vec2-urdufinetuned
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 3.6089
21
+ - Wer: 1.0
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: 0.001
41
+ - train_batch_size: 10
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 100
47
+ - num_epochs: 4
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:---:|
54
+ | 10.903 | 0.06 | 100 | 3.7302 | 1.0 |
55
+ | 3.6693 | 0.11 | 200 | 3.6193 | 1.0 |
56
+ | 3.6908 | 0.17 | 300 | 3.6678 | 1.0 |
57
+ | 3.6565 | 0.22 | 400 | 3.6365 | 1.0 |
58
+ | 3.6348 | 0.28 | 500 | 3.6443 | 1.0 |
59
+ | 3.6878 | 0.33 | 600 | 3.6583 | 1.0 |
60
+ | 3.572 | 0.39 | 700 | 3.6304 | 1.0 |
61
+ | 3.6749 | 0.44 | 800 | 3.6420 | 1.0 |
62
+ | 3.6872 | 0.5 | 900 | 3.6469 | 1.0 |
63
+ | 3.6594 | 0.56 | 1000 | 3.6278 | 1.0 |
64
+ | 3.6131 | 0.61 | 1100 | 3.6169 | 1.0 |
65
+ | 3.5748 | 0.67 | 1200 | 3.6234 | 1.0 |
66
+ | 3.6181 | 0.72 | 1300 | 3.6494 | 1.0 |
67
+ | 3.6164 | 0.78 | 1400 | 3.6248 | 1.0 |
68
+ | 3.6688 | 0.83 | 1500 | 3.6610 | 1.0 |
69
+ | 4.1978 | 0.89 | 1600 | 3.6903 | 1.0 |
70
+ | 3.7485 | 0.94 | 1700 | 3.6275 | 1.0 |
71
+ | 3.649 | 1.0 | 1800 | 3.6139 | 1.0 |
72
+ | 3.5834 | 1.06 | 1900 | 3.6161 | 1.0 |
73
+ | 3.6338 | 1.11 | 2000 | 3.6647 | 1.0 |
74
+ | 3.5427 | 1.17 | 2100 | 3.6129 | 1.0 |
75
+ | 3.6117 | 1.22 | 2200 | 3.6084 | 1.0 |
76
+ | 3.6726 | 1.28 | 2300 | 3.6149 | 1.0 |
77
+ | 3.6278 | 1.33 | 2400 | 3.6342 | 1.0 |
78
+ | 3.6746 | 1.39 | 2500 | 3.6102 | 1.0 |
79
+ | 3.574 | 1.44 | 2600 | 3.7048 | 1.0 |
80
+ | 3.5892 | 1.5 | 2700 | 3.6126 | 1.0 |
81
+ | 3.6575 | 1.56 | 2800 | 3.6163 | 1.0 |
82
+ | 3.592 | 1.61 | 2900 | 3.6610 | 1.0 |
83
+ | 3.6506 | 1.67 | 3000 | 3.6127 | 1.0 |
84
+ | 3.5823 | 1.72 | 3100 | 3.6071 | 1.0 |
85
+ | 3.6674 | 1.78 | 3200 | 3.6032 | 1.0 |
86
+ | 3.6017 | 1.83 | 3300 | 3.6236 | 1.0 |
87
+ | 3.5865 | 1.89 | 3400 | 3.6208 | 1.0 |
88
+ | 3.646 | 1.94 | 3500 | 3.6074 | 1.0 |
89
+ | 3.6042 | 2.0 | 3600 | 3.6442 | 1.0 |
90
+ | 3.56 | 2.06 | 3700 | 3.6076 | 1.0 |
91
+ | 3.6241 | 2.11 | 3800 | 3.6051 | 1.0 |
92
+ | 3.6245 | 2.17 | 3900 | 3.6074 | 1.0 |
93
+ | 3.5764 | 2.22 | 4000 | 3.6238 | 1.0 |
94
+ | 3.6168 | 2.28 | 4100 | 3.6192 | 1.0 |
95
+ | 3.6143 | 2.33 | 4200 | 3.6093 | 1.0 |
96
+ | 3.613 | 2.39 | 4300 | 3.6123 | 1.0 |
97
+ | 3.6178 | 2.44 | 4400 | 3.6135 | 1.0 |
98
+ | 3.6234 | 2.5 | 4500 | 3.6161 | 1.0 |
99
+ | 3.5833 | 2.56 | 4600 | 3.6064 | 1.0 |
100
+ | 3.5759 | 2.61 | 4700 | 3.6077 | 1.0 |
101
+ | 3.6747 | 2.67 | 4800 | 3.6123 | 1.0 |
102
+ | 3.5914 | 2.72 | 4900 | 3.6041 | 1.0 |
103
+ | 3.6342 | 2.78 | 5000 | 3.6208 | 1.0 |
104
+ | 3.5883 | 2.83 | 5100 | 3.6056 | 1.0 |
105
+ | 3.5563 | 2.89 | 5200 | 3.6159 | 1.0 |
106
+ | 3.6213 | 2.94 | 5300 | 3.6173 | 1.0 |
107
+ | 3.6507 | 3.0 | 5400 | 3.6031 | 1.0 |
108
+ | 3.549 | 3.06 | 5500 | 3.6371 | 1.0 |
109
+ | 3.5712 | 3.11 | 5600 | 3.6049 | 1.0 |
110
+ | 3.5731 | 3.17 | 5700 | 3.6273 | 1.0 |
111
+ | 3.6232 | 3.22 | 5800 | 3.6012 | 1.0 |
112
+ | 3.6406 | 3.28 | 5900 | 3.6020 | 1.0 |
113
+ | 3.6456 | 3.33 | 6000 | 3.6015 | 1.0 |
114
+ | 3.6268 | 3.39 | 6100 | 3.6047 | 1.0 |
115
+ | 3.6286 | 3.44 | 6200 | 3.6023 | 1.0 |
116
+ | 3.609 | 3.5 | 6300 | 3.6053 | 1.0 |
117
+ | 3.6256 | 3.56 | 6400 | 3.6040 | 1.0 |
118
+ | 3.5537 | 3.61 | 6500 | 3.6075 | 1.0 |
119
+ | 3.5214 | 3.67 | 6600 | 3.6055 | 1.0 |
120
+ | 3.6031 | 3.72 | 6700 | 3.6156 | 1.0 |
121
+ | 3.6624 | 3.78 | 6800 | 3.6037 | 1.0 |
122
+ | 3.5813 | 3.83 | 6900 | 3.6030 | 1.0 |
123
+ | 3.6514 | 3.89 | 7000 | 3.6043 | 1.0 |
124
+ | 3.5535 | 3.94 | 7100 | 3.6091 | 1.0 |
125
+ | 3.5954 | 4.0 | 7200 | 3.6089 | 1.0 |
126
+
127
+
128
+ ### Framework versions
129
+
130
+ - Transformers 4.36.0.dev0
131
+ - Pytorch 2.1.0+cu118
132
+ - Datasets 2.14.6
133
+ - Tokenizers 0.14.1