Jungwoo4021 commited on
Commit
9198879
1 Parent(s): a0a5034

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +74 -0
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - superb
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: wav2vec2-base-ks-finetuning
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # wav2vec2-base-ks-finetuning
18
+
19
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2050
22
+ - Accuracy: 0.9813
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: 3e-05
42
+ - train_batch_size: 256
43
+ - eval_batch_size: 256
44
+ - seed: 0
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 1024
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 10.0
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
57
+ | 1.6773 | 1.0 | 50 | 1.6218 | 0.6209 |
58
+ | 1.4707 | 2.0 | 100 | 1.4400 | 0.6209 |
59
+ | 1.1387 | 3.0 | 150 | 1.0470 | 0.6599 |
60
+ | 0.7909 | 4.0 | 200 | 0.6997 | 0.8903 |
61
+ | 0.5488 | 5.0 | 250 | 0.4567 | 0.9640 |
62
+ | 0.4195 | 6.0 | 300 | 0.3288 | 0.9754 |
63
+ | 0.3445 | 7.0 | 350 | 0.2598 | 0.9809 |
64
+ | 0.3107 | 8.0 | 400 | 0.2261 | 0.9813 |
65
+ | 0.2781 | 9.0 | 450 | 0.2104 | 0.9810 |
66
+ | 0.2729 | 10.0 | 500 | 0.2050 | 0.9813 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.22.0.dev0
72
+ - Pytorch 1.11.0+cu115
73
+ - Datasets 2.4.0
74
+ - Tokenizers 0.12.1