thisisHJLee
commited on
Commit
•
217653d
1
Parent(s):
a4b00e7
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: wav2vec2-large-xls-r-300m-korean-g
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# wav2vec2-large-xls-r-300m-korean-g
|
14 |
+
|
15 |
+
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.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.9226
|
18 |
+
- Cer: 0.1638
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0001
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- lr_scheduler_warmup_steps: 1000
|
44 |
+
- num_epochs: 30
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
51 |
+
| 4.8333 | 3.25 | 500 | 3.4624 | 0.9560 |
|
52 |
+
| 1.243 | 6.49 | 1000 | 1.0049 | 0.2488 |
|
53 |
+
| 0.3657 | 9.74 | 1500 | 0.8749 | 0.2087 |
|
54 |
+
| 0.2104 | 12.99 | 2000 | 0.8799 | 0.1909 |
|
55 |
+
| 0.1508 | 16.23 | 2500 | 0.9321 | 0.1845 |
|
56 |
+
| 0.1245 | 19.48 | 3000 | 0.8778 | 0.1744 |
|
57 |
+
| 0.1048 | 22.73 | 3500 | 0.9793 | 0.1808 |
|
58 |
+
| 0.0922 | 25.97 | 4000 | 0.9464 | 0.1697 |
|
59 |
+
| 0.0801 | 29.22 | 4500 | 0.9226 | 0.1638 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.17.0
|
65 |
+
- Pytorch 1.10.0+cu113
|
66 |
+
- Datasets 1.18.3
|
67 |
+
- Tokenizers 0.13.0
|