Hugging Face's logo

karanthgreeshma
/
wav2vec2-large-300m-colab-only-gn

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
karanthgreeshma commited on
Commit
877248c
•
1 Parent(s): 89bddb2

End of training

Browse files
Files changed (1) hide show
  1. README.md +143 -0
README.md ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - common_voice_13_0
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: wav2vec2-large-300m-colab-only-gn
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: common_voice_13_0
18
+ type: common_voice_13_0
19
+ config: gn
20
+ split: test
21
+ args: gn
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.5229303156640858
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # wav2vec2-large-300m-colab-only-gn
32
+
33
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.5274
36
+ - Wer: 0.5229
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.0003
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 32
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_steps: 100
64
+ - num_epochs: 30
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 20.8148 | 0.45 | 25 | 13.5976 | 1.0 |
71
+ | 7.0188 | 0.9 | 50 | 5.5263 | 1.0 |
72
+ | 4.1285 | 1.35 | 75 | 3.6078 | 1.0 |
73
+ | 3.338 | 1.8 | 100 | 3.3217 | 1.0 |
74
+ | 3.2829 | 2.25 | 125 | 3.2781 | 1.0 |
75
+ | 3.272 | 2.7 | 150 | 3.2601 | 1.0 |
76
+ | 3.2224 | 3.15 | 175 | 3.2234 | 1.0 |
77
+ | 3.1949 | 3.6 | 200 | 3.1998 | 1.0 |
78
+ | 3.1846 | 4.05 | 225 | 3.1841 | 1.0 |
79
+ | 3.1615 | 4.5 | 250 | 3.1719 | 1.0 |
80
+ | 3.1367 | 4.95 | 275 | 3.1132 | 1.0 |
81
+ | 3.0111 | 5.41 | 300 | 2.9344 | 1.0 |
82
+ | 2.7786 | 5.86 | 325 | 2.5643 | 1.0 |
83
+ | 2.2106 | 6.31 | 350 | 1.8132 | 1.0 |
84
+ | 1.6365 | 6.76 | 375 | 1.4008 | 0.9982 |
85
+ | 1.178 | 7.21 | 400 | 1.0678 | 0.9845 |
86
+ | 0.8903 | 7.66 | 425 | 0.8744 | 0.9369 |
87
+ | 0.7429 | 8.11 | 450 | 0.7213 | 0.8752 |
88
+ | 0.5931 | 8.56 | 475 | 0.6681 | 0.8189 |
89
+ | 0.5592 | 9.01 | 500 | 0.6622 | 0.7895 |
90
+ | 0.4316 | 9.46 | 525 | 0.6177 | 0.7644 |
91
+ | 0.4098 | 9.91 | 550 | 0.5599 | 0.7874 |
92
+ | 0.3176 | 10.36 | 575 | 0.5649 | 0.7001 |
93
+ | 0.3142 | 10.81 | 600 | 0.5828 | 0.6867 |
94
+ | 0.3227 | 11.26 | 625 | 0.5505 | 0.6736 |
95
+ | 0.275 | 11.71 | 650 | 0.5432 | 0.6540 |
96
+ | 0.2783 | 12.16 | 675 | 0.5372 | 0.6462 |
97
+ | 0.2316 | 12.61 | 700 | 0.5078 | 0.6379 |
98
+ | 0.2281 | 13.06 | 725 | 0.5059 | 0.6161 |
99
+ | 0.2191 | 13.51 | 750 | 0.5175 | 0.5956 |
100
+ | 0.1911 | 13.96 | 775 | 0.5216 | 0.5929 |
101
+ | 0.1731 | 14.41 | 800 | 0.5069 | 0.5789 |
102
+ | 0.1743 | 14.86 | 825 | 0.5207 | 0.5971 |
103
+ | 0.1755 | 15.32 | 850 | 0.5436 | 0.6307 |
104
+ | 0.1568 | 15.77 | 875 | 0.5374 | 0.6001 |
105
+ | 0.1629 | 16.22 | 900 | 0.5429 | 0.6102 |
106
+ | 0.1418 | 16.67 | 925 | 0.5089 | 0.5762 |
107
+ | 0.136 | 17.12 | 950 | 0.5291 | 0.5878 |
108
+ | 0.1354 | 17.57 | 975 | 0.5381 | 0.5840 |
109
+ | 0.1351 | 18.02 | 1000 | 0.5511 | 0.5947 |
110
+ | 0.1252 | 18.47 | 1025 | 0.5204 | 0.5643 |
111
+ | 0.1215 | 18.92 | 1050 | 0.5385 | 0.5613 |
112
+ | 0.1188 | 19.37 | 1075 | 0.5063 | 0.5718 |
113
+ | 0.1209 | 19.82 | 1100 | 0.5211 | 0.5488 |
114
+ | 0.1091 | 20.27 | 1125 | 0.5245 | 0.5557 |
115
+ | 0.112 | 20.72 | 1150 | 0.4910 | 0.5587 |
116
+ | 0.102 | 21.17 | 1175 | 0.5192 | 0.5581 |
117
+ | 0.0947 | 21.62 | 1200 | 0.5500 | 0.5718 |
118
+ | 0.1066 | 22.07 | 1225 | 0.5288 | 0.5488 |
119
+ | 0.1011 | 22.52 | 1250 | 0.5180 | 0.5438 |
120
+ | 0.0974 | 22.97 | 1275 | 0.5089 | 0.5277 |
121
+ | 0.0926 | 23.42 | 1300 | 0.5222 | 0.5301 |
122
+ | 0.0871 | 23.87 | 1325 | 0.5135 | 0.5366 |
123
+ | 0.0808 | 24.32 | 1350 | 0.4990 | 0.5331 |
124
+ | 0.0739 | 24.77 | 1375 | 0.5281 | 0.5351 |
125
+ | 0.0841 | 25.23 | 1400 | 0.5321 | 0.5360 |
126
+ | 0.0743 | 25.68 | 1425 | 0.5508 | 0.5447 |
127
+ | 0.0809 | 26.13 | 1450 | 0.5228 | 0.5396 |
128
+ | 0.0631 | 26.58 | 1475 | 0.5284 | 0.5351 |
129
+ | 0.0788 | 27.03 | 1500 | 0.5250 | 0.5289 |
130
+ | 0.0754 | 27.48 | 1525 | 0.5204 | 0.5259 |
131
+ | 0.0663 | 27.93 | 1550 | 0.5275 | 0.5313 |
132
+ | 0.0645 | 28.38 | 1575 | 0.5288 | 0.5259 |
133
+ | 0.0729 | 28.83 | 1600 | 0.5268 | 0.5259 |
134
+ | 0.0656 | 29.28 | 1625 | 0.5277 | 0.5232 |
135
+ | 0.0703 | 29.73 | 1650 | 0.5274 | 0.5229 |
136
+
137
+
138
+ ### Framework versions
139
+
140
+ - Transformers 4.34.1
141
+ - Pytorch 2.0.1+cu118
142
+ - Datasets 2.14.6
143
+ - Tokenizers 0.14.1