update model card README.md
Browse files
README.md
CHANGED
@@ -12,10 +12,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# wav2vec2-base-timit-demo-colab-1
|
14 |
|
15 |
-
This model is a fine-tuned version of [
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 0.
|
18 |
-
- Wer: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -34,27 +34,29 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- learning_rate: 0.
|
38 |
- train_batch_size: 6
|
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: 800
|
44 |
-
- num_epochs:
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
51 |
-
|
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
12 |
|
13 |
# wav2vec2-base-timit-demo-colab-1
|
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: 0.9634
|
18 |
+
- Wer: 0.4398
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0002
|
38 |
- train_batch_size: 6
|
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: 800
|
44 |
+
- num_epochs: 50
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
51 |
+
| 4.8991 | 5.26 | 500 | 1.4319 | 0.7522 |
|
52 |
+
| 0.8555 | 10.53 | 1000 | 0.7895 | 0.5818 |
|
53 |
+
| 0.4584 | 15.79 | 1500 | 0.7198 | 0.5211 |
|
54 |
+
| 0.3096 | 21.05 | 2000 | 0.7983 | 0.5118 |
|
55 |
+
| 0.2165 | 26.32 | 2500 | 0.7893 | 0.4745 |
|
56 |
+
| 0.163 | 31.58 | 3000 | 0.8779 | 0.4589 |
|
57 |
+
| 0.1144 | 36.84 | 3500 | 0.9256 | 0.4540 |
|
58 |
+
| 0.0886 | 42.11 | 4000 | 0.9184 | 0.4530 |
|
59 |
+
| 0.0668 | 47.37 | 4500 | 0.9634 | 0.4398 |
|
60 |
|
61 |
|
62 |
### Framework versions
|