Steven Liu
commited on
Commit
•
1cb4ba3
1
Parent(s):
f2036df
update model card README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
- Wer: 1.0
|
21 |
|
22 |
## Model description
|
@@ -36,30 +36,25 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate: 0.
|
40 |
- train_batch_size: 8
|
41 |
- eval_batch_size: 8
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_ratio: 0.1
|
46 |
-
- num_epochs:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
53 |
-
|
|
54 |
-
| 1.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 1.
|
58 |
-
| 0.9615 | 6.0 | 228 | 0.9643 | 1.0 |
|
59 |
-
| 0.9693 | 7.0 | 266 | 0.9562 | 1.0 |
|
60 |
-
| 0.943 | 8.0 | 304 | 1.0394 | 1.0 |
|
61 |
-
| 0.9586 | 9.0 | 342 | 0.9711 | 1.0 |
|
62 |
-
| 0.9166 | 10.0 | 380 | 0.9568 | 1.0 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.0301
|
20 |
- Wer: 1.0
|
21 |
|
22 |
## Model description
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0001
|
40 |
- train_batch_size: 8
|
41 |
- eval_batch_size: 8
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_ratio: 0.1
|
46 |
+
- num_epochs: 5
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
53 |
+
| 2.8297 | 1.0 | 54 | 2.3505 | 1.0 |
|
54 |
+
| 1.1947 | 2.0 | 108 | 1.1780 | 1.0 |
|
55 |
+
| 0.9963 | 3.0 | 162 | 1.1032 | 1.0 |
|
56 |
+
| 0.9692 | 4.0 | 216 | 1.0481 | 1.0 |
|
57 |
+
| 1.0141 | 5.0 | 270 | 1.0301 | 1.0 |
|
|
|
|
|
|
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|