gary109 commited on
Commit
7372ac0
1 Parent(s): 84fb003

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v3
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v3
13
+
14
+ This model is a fine-tuned version of [gary109/ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v1](https://huggingface.co/gary109/ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v1) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 0.4702
17
+ - Wer: 0.1546
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 1e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 2
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 16
41
+ - total_train_batch_size: 32
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_steps: 500
45
+ - num_epochs: 10.0
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
51
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 0.1517 | 1.0 | 552 | 0.4301 | 0.1633 |
53
+ | 0.1309 | 2.0 | 1104 | 0.4348 | 0.1629 |
54
+ | 0.1237 | 3.0 | 1656 | 0.4611 | 0.1604 |
55
+ | 0.1056 | 4.0 | 2208 | 0.4541 | 0.1574 |
56
+ | 0.1236 | 5.0 | 2760 | 0.4669 | 0.1603 |
57
+ | 0.1118 | 6.0 | 3312 | 0.4640 | 0.1567 |
58
+ | 0.0916 | 7.0 | 3864 | 0.4678 | 0.1555 |
59
+ | 0.1 | 8.0 | 4416 | 0.4705 | 0.1550 |
60
+ | 0.1301 | 9.0 | 4968 | 0.4740 | 0.1551 |
61
+ | 0.0885 | 10.0 | 5520 | 0.4702 | 0.1546 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.21.0.dev0
67
+ - Pytorch 1.9.1+cu102
68
+ - Datasets 2.3.3.dev0
69
+ - Tokenizers 0.12.1