update model card README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
# mst_1
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -41,6 +44,18 @@ The following hyperparameters were used during training:
|
|
| 41 |
- num_epochs: 7
|
| 42 |
- mixed_precision_training: Native AMP
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- Transformers 4.17.0
|
|
|
|
| 13 |
# mst_1
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.0038
|
| 18 |
+
- Wer: 0.9915
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 44 |
- num_epochs: 7
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 51 |
+
| 11.0362 | 1.15 | 500 | 2.7219 | 1.0 |
|
| 52 |
+
| 1.9536 | 2.29 | 1000 | 0.5060 | 2.0274 |
|
| 53 |
+
| 0.2347 | 3.44 | 1500 | 0.0268 | 1.0462 |
|
| 54 |
+
| 0.0633 | 4.59 | 2000 | 0.0078 | 1.0 |
|
| 55 |
+
| 0.0359 | 5.73 | 2500 | 0.0047 | 0.9949 |
|
| 56 |
+
| 0.014 | 6.88 | 3000 | 0.0038 | 0.9915 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- Transformers 4.17.0
|