Commit
·
3eeefcf
1
Parent(s):
374da45
update model description to fit checkpoint
Browse files
README.md
CHANGED
|
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Wer:
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -49,14 +49,14 @@ The following hyperparameters were used during training:
|
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- lr_scheduler_warmup_steps: 500
|
| 52 |
-
- training_steps:
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
-
| Training Loss |
|
| 58 |
-
|
| 59 |
-
| 0.5426 |
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.30
|
| 24 |
+
- Wer: 20.66
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- lr_scheduler_warmup_steps: 500
|
| 52 |
+
- training_steps: 1500
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
+
| Training Loss | Step | Validation Loss | Wer |
|
| 58 |
+
|:-------------:|:----:|:---------------:|:-------:|
|
| 59 |
+
| 0.5426 | 1500 | 0.30 | 20.66 |
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|