Hugging Face's logo

yip-i
/
torgo_xlsr_finetune-M04-2

Automatic Speech Recognition
Transformers
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
yip-i commited on
Commit
f2baa0c
•
1 Parent(s): 300e86e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: torgo_xlsr_finetune-M04-2
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-M04-2
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: 2.2407
20
+ - Wer: 1.2835
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
+ | 22.4872 | 0.88 | 500 | 3.2706 | 1.0 |
53
+ | 3.361 | 1.75 | 1000 | 2.8365 | 1.0 |
54
+ | 2.8532 | 2.63 | 1500 | 2.7444 | 1.0 |
55
+ | 2.5391 | 3.5 | 2000 | 2.1105 | 1.0824 |
56
+ | 1.6217 | 4.38 | 2500 | 1.7736 | 1.6424 |
57
+ | 1.1107 | 5.25 | 3000 | 1.5937 | 1.4918 |
58
+ | 0.8277 | 6.13 | 3500 | 1.5655 | 1.4729 |
59
+ | 0.6872 | 7.01 | 4000 | 1.6192 | 1.4671 |
60
+ | 0.5597 | 7.88 | 4500 | 1.6735 | 1.4176 |
61
+ | 0.4942 | 8.76 | 5000 | 1.5915 | 1.3847 |
62
+ | 0.4447 | 9.63 | 5500 | 1.8509 | 1.4506 |
63
+ | 0.3967 | 10.51 | 6000 | 1.7833 | 1.3929 |
64
+ | 0.3596 | 11.38 | 6500 | 2.0147 | 1.3776 |
65
+ | 0.3409 | 12.26 | 7000 | 1.8649 | 1.4 |
66
+ | 0.3169 | 13.13 | 7500 | 1.8252 | 1.3541 |
67
+ | 0.2962 | 14.01 | 8000 | 2.1108 | 1.3906 |
68
+ | 0.2934 | 14.89 | 8500 | 1.8004 | 1.3188 |
69
+ | 0.2564 | 15.76 | 9000 | 1.8681 | 1.3659 |
70
+ | 0.2447 | 16.64 | 9500 | 1.9341 | 1.3318 |
71
+ | 0.2248 | 17.51 | 10000 | 2.0251 | 1.3259 |
72
+ | 0.2234 | 18.39 | 10500 | 1.9982 | 1.2988 |
73
+ | 0.1955 | 19.26 | 11000 | 2.0277 | 1.3024 |
74
+ | 0.1882 | 20.14 | 11500 | 2.0001 | 1.2882 |
75
+ | 0.2022 | 21.02 | 12000 | 1.9842 | 1.2988 |
76
+ | 0.163 | 21.89 | 12500 | 1.9931 | 1.32 |
77
+ | 0.1732 | 22.77 | 13000 | 2.0577 | 1.2659 |
78
+ | 0.1522 | 23.64 | 13500 | 2.0511 | 1.2812 |
79
+ | 0.1367 | 24.52 | 14000 | 2.0308 | 1.2671 |
80
+ | 0.1393 | 25.39 | 14500 | 2.2392 | 1.2788 |
81
+ | 0.1407 | 26.27 | 15000 | 2.1329 | 1.2824 |
82
+ | 0.1244 | 27.15 | 15500 | 2.0721 | 1.2694 |
83
+ | 0.116 | 28.02 | 16000 | 2.1656 | 1.2824 |
84
+ | 0.125 | 28.9 | 16500 | 2.2338 | 1.2882 |
85
+ | 0.1063 | 29.77 | 17000 | 2.2407 | 1.2835 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.26.1
91
+ - Pytorch 1.13.1+cu116
92
+ - Datasets 1.18.3
93
+ - Tokenizers 0.13.2