Hugging Face's logo

xacl
/
wav2vec2-base-timit-demo-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xacl commited on
Commit
183ebc9
•
1 Parent(s): 744449a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +90 -0
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2-base-timit-demo-colab
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-base-timit-demo-colab
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5532
21
+ - Wer: 0.3373
22
+ - Cer: 0.1112
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0001
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 1000
48
+ - num_epochs: 30
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
54
+ | 0.1293 | 1.0 | 500 | 0.3918 | 0.3677 | 0.1170 |
55
+ | 0.133 | 2.01 | 1000 | 0.4392 | 0.3797 | 0.1234 |
56
+ | 0.1473 | 3.01 | 1500 | 0.4959 | 0.3914 | 0.1267 |
57
+ | 0.1373 | 4.02 | 2000 | 0.4781 | 0.3851 | 0.1260 |
58
+ | 0.1259 | 5.02 | 2500 | 0.4473 | 0.3810 | 0.1237 |
59
+ | 0.1123 | 6.02 | 3000 | 0.5314 | 0.3774 | 0.1243 |
60
+ | 0.1086 | 7.03 | 3500 | 0.4231 | 0.3801 | 0.1228 |
61
+ | 0.0956 | 8.03 | 4000 | 0.5203 | 0.3734 | 0.1236 |
62
+ | 0.0839 | 9.04 | 4500 | 0.5310 | 0.3750 | 0.1227 |
63
+ | 0.0778 | 10.04 | 5000 | 0.5279 | 0.3793 | 0.1257 |
64
+ | 0.0772 | 11.04 | 5500 | 0.4969 | 0.3792 | 0.1265 |
65
+ | 0.072 | 12.05 | 6000 | 0.5489 | 0.3701 | 0.1239 |
66
+ | 0.0678 | 13.05 | 6500 | 0.5123 | 0.3669 | 0.1207 |
67
+ | 0.067 | 14.06 | 7000 | 0.4969 | 0.3663 | 0.1192 |
68
+ | 0.061 | 15.06 | 7500 | 0.4742 | 0.3664 | 0.1212 |
69
+ | 0.0575 | 16.06 | 8000 | 0.5304 | 0.3643 | 0.1194 |
70
+ | 0.0574 | 17.07 | 8500 | 0.4936 | 0.3729 | 0.1218 |
71
+ | 0.0474 | 18.07 | 9000 | 0.5363 | 0.3601 | 0.1185 |
72
+ | 0.0447 | 19.08 | 9500 | 0.5347 | 0.3552 | 0.1177 |
73
+ | 0.0372 | 20.08 | 10000 | 0.5372 | 0.3519 | 0.1157 |
74
+ | 0.0325 | 21.08 | 10500 | 0.5455 | 0.3525 | 0.1159 |
75
+ | 0.0309 | 22.09 | 11000 | 0.5193 | 0.3514 | 0.1146 |
76
+ | 0.0314 | 23.09 | 11500 | 0.5402 | 0.3494 | 0.1160 |
77
+ | 0.0272 | 24.1 | 12000 | 0.5309 | 0.3457 | 0.1129 |
78
+ | 0.0238 | 25.1 | 12500 | 0.5490 | 0.3447 | 0.1132 |
79
+ | 0.0217 | 26.1 | 13000 | 0.5702 | 0.3406 | 0.1117 |
80
+ | 0.0225 | 27.11 | 13500 | 0.5575 | 0.3414 | 0.1116 |
81
+ | 0.0189 | 28.11 | 14000 | 0.5572 | 0.3391 | 0.1115 |
82
+ | 0.0179 | 29.12 | 14500 | 0.5532 | 0.3373 | 0.1112 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.32.0.dev0
88
+ - Pytorch 2.0.1+cu118
89
+ - Datasets 1.18.3
90
+ - Tokenizers 0.13.3