Commit
•
961bc5f
1
Parent(s):
8b3c871
update model card README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the commonvoice dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -47,15 +47,17 @@ The following hyperparameters were used during training:
|
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- lr_scheduler_warmup_steps: 500
|
| 50 |
-
- training_steps:
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the commonvoice dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.4261
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- training_steps: 4000
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 0.4543 | 13.61 | 1000 | 0.4225 |
|
| 58 |
+
| 0.4525 | 27.21 | 2000 | 0.4203 |
|
| 59 |
+
| 0.4359 | 40.82 | 3000 | 0.4228 |
|
| 60 |
+
| 0.4324 | 54.42 | 4000 | 0.4261 |
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|