Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ This model is a fine-tuned version of [sesame/csm-1b](https://huggingface.co/ses
|
|
| 17 |
|
| 18 |
The sound quality seems to be better than tuning on full-parameters. However, more tweaking would be needed to ensure consistent performance. From the sample we can hear two distinct sounds (soft and vibrant) when prompt differently. Also, model performance on larger tokens will be to be further validated.
|
| 19 |
|
|
|
|
|
|
|
| 20 |
## Model Details
|
| 21 |
- **Base Model**: sesame/csm-1b
|
| 22 |
- **Training Data**: MrDragonFox/Elise dataset
|
|
|
|
| 17 |
|
| 18 |
The sound quality seems to be better than tuning on full-parameters. However, more tweaking would be needed to ensure consistent performance. From the sample we can hear two distinct sounds (soft and vibrant) when prompt differently. Also, model performance on larger tokens will be to be further validated.
|
| 19 |
|
| 20 |
+
Larger training data would be required for more consistent sound effect as the current dataset is small and limited.
|
| 21 |
+
|
| 22 |
## Model Details
|
| 23 |
- **Base Model**: sesame/csm-1b
|
| 24 |
- **Training Data**: MrDragonFox/Elise dataset
|