update model card README.md
Browse files
README.md
CHANGED
@@ -1 +1,66 @@
|
|
1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: wav2vec2-base-cynthia-timit
|
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-base-cynthia-timit
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.4607
|
18 |
+
- Wer: 0.1903
|
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: 32
|
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 | Wer |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
51 |
+
| 0.0689 | 3.45 | 500 | 0.3667 | 0.1970 |
|
52 |
+
| 0.0758 | 6.9 | 1000 | 0.4734 | 0.2154 |
|
53 |
+
| 0.0581 | 10.34 | 1500 | 0.4375 | 0.2179 |
|
54 |
+
| 0.0468 | 13.79 | 2000 | 0.4866 | 0.2112 |
|
55 |
+
| 0.0408 | 17.24 | 2500 | 0.5170 | 0.2043 |
|
56 |
+
| 0.0365 | 20.69 | 3000 | 0.5125 | 0.1987 |
|
57 |
+
| 0.0323 | 24.14 | 3500 | 0.4754 | 0.2008 |
|
58 |
+
| 0.0297 | 27.59 | 4000 | 0.4607 | 0.1903 |
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- Transformers 4.11.3
|
64 |
+
- Pytorch 1.10.0+cu102
|
65 |
+
- Datasets 1.14.0
|
66 |
+
- Tokenizers 0.10.3
|