monideep2255
commited on
Commit
•
c96649c
1
Parent(s):
e19914b
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: pseudolabeling-step1-F04
|
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 |
+
# pseudolabeling-step1-F04
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [yongjian/wav2vec2-large-a](https://huggingface.co/yongjian/wav2vec2-large-a) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.5392
|
17 |
+
- Wer: 0.8870
|
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: 0.0001
|
37 |
+
- train_batch_size: 8
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- lr_scheduler_warmup_steps: 1000
|
43 |
+
- num_epochs: 30
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
49 |
+
| 21.4261 | 1.71 | 500 | 3.2064 | 1.0 |
|
50 |
+
| 2.9275 | 3.42 | 1000 | 2.6461 | 1.2637 |
|
51 |
+
| 2.49 | 5.14 | 1500 | 2.0627 | 1.2527 |
|
52 |
+
| 1.8582 | 6.85 | 2000 | 1.6367 | 1.1978 |
|
53 |
+
| 1.5071 | 8.56 | 2500 | 1.2845 | 1.1743 |
|
54 |
+
| 1.2181 | 10.27 | 3000 | 1.1395 | 1.1586 |
|
55 |
+
| 1.0386 | 11.99 | 3500 | 1.0155 | 1.0926 |
|
56 |
+
| 0.9307 | 13.7 | 4000 | 0.8144 | 1.0628 |
|
57 |
+
| 0.8073 | 15.41 | 4500 | 0.7666 | 1.1146 |
|
58 |
+
| 0.7209 | 17.12 | 5000 | 0.7020 | 1.0911 |
|
59 |
+
| 0.6618 | 18.84 | 5500 | 0.6829 | 1.0612 |
|
60 |
+
| 0.6079 | 20.55 | 6000 | 0.6023 | 0.9937 |
|
61 |
+
| 0.5242 | 22.26 | 6500 | 0.6057 | 0.9827 |
|
62 |
+
| 0.4848 | 23.97 | 7000 | 0.5802 | 0.9435 |
|
63 |
+
| 0.4602 | 25.68 | 7500 | 0.5376 | 0.9027 |
|
64 |
+
| 0.446 | 27.4 | 8000 | 0.5351 | 0.8964 |
|
65 |
+
| 0.4245 | 29.11 | 8500 | 0.5392 | 0.8870 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.23.1
|
71 |
+
- Pytorch 1.12.1+cu113
|
72 |
+
- Datasets 1.18.3
|
73 |
+
- Tokenizers 0.13.2
|