update model card README.md
Browse files
README.md
CHANGED
|
@@ -14,8 +14,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 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 |
-
-
|
| 18 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -44,16 +49,6 @@ The following hyperparameters were used during training:
|
|
| 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 |
-
| 5.2285 | 7.04 | 500 | 3.1669 | 1.0 |
|
| 52 |
-
| 3.1252 | 14.08 | 1000 | 3.1526 | 1.0 |
|
| 53 |
-
| 3.1214 | 21.13 | 1500 | 3.1573 | 1.0 |
|
| 54 |
-
| 3.1172 | 28.17 | 2000 | 3.1652 | 1.0 |
|
| 55 |
-
|
| 56 |
-
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.11.3
|
|
|
|
| 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 |
+
- eval_loss: 0.6367
|
| 18 |
+
- eval_wer: 0.5855
|
| 19 |
+
- eval_runtime: 20.4889
|
| 20 |
+
- eval_samples_per_second: 6.931
|
| 21 |
+
- eval_steps_per_second: 0.879
|
| 22 |
+
- epoch: 14.08
|
| 23 |
+
- step: 1000
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 49 |
- num_epochs: 30
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
### Framework versions
|
| 53 |
|
| 54 |
- Transformers 4.11.3
|