Hugging Face's logo

yip-i
/
torgo_xlsr_finetune-F03-2

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
yip-i commited on
Commit
1f82124
•
1 Parent(s): 891e631

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: torgo_xlsr_finetune-F03-2
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # torgo_xlsr_finetune-F03-2
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.5454
20
+ - Wer: 0.8555
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 1000
46
+ - num_epochs: 30
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
52
+ | 25.1806 | 0.97 | 500 | 3.3512 | 1.0 |
53
+ | 3.3648 | 1.94 | 1000 | 3.1566 | 1.0 |
54
+ | 2.9865 | 2.91 | 1500 | 2.8249 | 1.0 |
55
+ | 2.8219 | 3.88 | 2000 | 2.7880 | 1.0 |
56
+ | 2.62 | 4.85 | 2500 | 2.4134 | 1.1793 |
57
+ | 2.0129 | 5.83 | 3000 | 1.7735 | 1.3777 |
58
+ | 1.3439 | 6.8 | 3500 | 1.4148 | 1.3656 |
59
+ | 0.9587 | 7.77 | 4000 | 1.3914 | 1.2437 |
60
+ | 0.7532 | 8.74 | 4500 | 1.2565 | 1.2957 |
61
+ | 0.6204 | 9.71 | 5000 | 1.2621 | 1.1074 |
62
+ | 0.5367 | 10.68 | 5500 | 1.3255 | 1.1199 |
63
+ | 0.4471 | 11.65 | 6000 | 1.2730 | 1.0789 |
64
+ | 0.3989 | 12.62 | 6500 | 1.2627 | 1.0258 |
65
+ | 0.3562 | 13.59 | 7000 | 1.3006 | 0.9754 |
66
+ | 0.3346 | 14.56 | 7500 | 1.2739 | 0.9598 |
67
+ | 0.2949 | 15.53 | 8000 | 1.3260 | 0.9238 |
68
+ | 0.2816 | 16.5 | 8500 | 1.3446 | 0.9152 |
69
+ | 0.2552 | 17.48 | 9000 | 1.3537 | 0.8848 |
70
+ | 0.2434 | 18.45 | 9500 | 1.3288 | 0.9258 |
71
+ | 0.2156 | 19.42 | 10000 | 1.3863 | 0.8812 |
72
+ | 0.2126 | 20.39 | 10500 | 1.3466 | 0.8867 |
73
+ | 0.1939 | 21.36 | 11000 | 1.4522 | 0.9113 |
74
+ | 0.1829 | 22.33 | 11500 | 1.5253 | 0.8922 |
75
+ | 0.179 | 23.3 | 12000 | 1.4589 | 0.8543 |
76
+ | 0.1684 | 24.27 | 12500 | 1.5436 | 0.8664 |
77
+ | 0.1516 | 25.24 | 13000 | 1.5324 | 0.8668 |
78
+ | 0.1472 | 26.21 | 13500 | 1.5561 | 0.8711 |
79
+ | 0.1399 | 27.18 | 14000 | 1.5400 | 0.8605 |
80
+ | 0.1405 | 28.16 | 14500 | 1.5626 | 0.8512 |
81
+ | 0.1349 | 29.13 | 15000 | 1.5454 | 0.8555 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.26.1
87
+ - Pytorch 1.13.1+cu116
88
+ - Datasets 1.18.3
89
+ - Tokenizers 0.13.2