Hugging Face's logo

slplab
/
5sents_XLS-R_2_e-4

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
Community
1
slplab commited on
Commit
52b2894
·
1 Parent(s): 77121bc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: 5sents_XLS-R_2_e-4
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
+ # 5sents_XLS-R_2_e-4
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.3629
20
+ - Wer: 0.2063
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: 32
41
+ - eval_batch_size: 32
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 128
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - training_steps: 400
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-------:|:----:|:---------------:|:------:|
54
+ | 70.1025 | 99.89 | 200 | 23.5652 | 1.0 |
55
+ | 17.8988 | 199.89 | 400 | 10.4265 | 1.0 |
56
+ | 7.3246 | 299.89 | 600 | 4.0969 | 1.0 |
57
+ | 3.5815 | 399.89 | 800 | 2.4899 | 1.0 |
58
+ | 1.4553 | 499.89 | 1000 | 1.3636 | 0.7354 |
59
+ | 0.3355 | 599.89 | 1200 | 1.4502 | 0.3651 |
60
+ | 0.1232 | 699.89 | 1400 | 0.8715 | 0.3280 |
61
+ | 0.0615 | 799.89 | 1600 | 0.9018 | 0.3968 |
62
+ | 0.0372 | 899.89 | 1800 | 1.7271 | 0.4339 |
63
+ | 0.0247 | 999.89 | 2000 | 0.6459 | 0.2751 |
64
+ | 0.0166 | 1099.89 | 2200 | 0.4516 | 0.2540 |
65
+ | 0.0216 | 1199.89 | 2400 | 0.6955 | 0.2487 |
66
+ | 0.0093 | 1299.89 | 2600 | 1.1281 | 0.2646 |
67
+ | 0.0084 | 1399.89 | 2800 | 0.6150 | 0.1376 |
68
+ | 0.0076 | 1499.89 | 3000 | 1.1476 | 0.2646 |
69
+ | 0.0125 | 1599.89 | 3200 | 1.0682 | 0.2487 |
70
+ | 0.0096 | 1699.89 | 3400 | 0.8676 | 0.2487 |
71
+ | 0.0121 | 1799.89 | 3600 | 2.8241 | 0.2963 |
72
+ | 0.0107 | 1899.89 | 3800 | 0.3758 | 0.2381 |
73
+ | 0.0107 | 1999.89 | 4000 | 0.8708 | 0.2381 |
74
+ | 0.0051 | 2099.89 | 4200 | 0.8423 | 0.2804 |
75
+ | 0.0081 | 2199.89 | 4400 | 0.9489 | 0.2698 |
76
+ | 0.0044 | 2299.89 | 4600 | 0.8984 | 0.2857 |
77
+ | 0.0026 | 2399.89 | 4800 | 0.5836 | 0.2328 |
78
+ | 0.0169 | 2499.89 | 5000 | 0.9432 | 0.2434 |
79
+ | 0.0055 | 2599.89 | 5200 | 0.4225 | 0.2381 |
80
+ | 0.0033 | 2699.89 | 5400 | 1.1866 | 0.1693 |
81
+ | 0.0019 | 2799.89 | 5600 | 0.6218 | 0.1746 |
82
+ | 0.002 | 2899.89 | 5800 | 0.3831 | 0.1799 |
83
+ | 0.0026 | 2999.89 | 6000 | 0.6229 | 0.1323 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.26.1
89
+ - Pytorch 2.0.1+cu118
90
+ - Datasets 2.11.0
91
+ - Tokenizers 0.13.3