Instructions to use SPRINGLab/SPRING_F5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SPRINGLab/SPRING_F5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="SPRINGLab/SPRING_F5", trust_remote_code=True)# Load model directly from transformers import SPRING_F5 model = SPRING_F5.from_pretrained("SPRINGLab/SPRING_F5", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -89,8 +89,6 @@ datasets:
|
|
| 89 |
|
| 90 |
**SPRING_F5** is a multilingual text-to-speech (TTS) model based on **F5-TTS**, fine-tuned to support **23 Indian Language & English**.
|
| 91 |
|
| 92 |
-
We further modified the **inference pipeline** to support **cross-lingual voice cloning**. This allows the model to preserve the voice characteristics of a reference speaker when generating speech in a different language. To achieve this, we modified the **duration estimation** during inference to better handle differences in speech duration across languages. As a result, reference speech in one supported language can be used to generate speech in another supported language.
|
| 93 |
-
|
| 94 |
## Supported Languages
|
| 95 |
|
| 96 |
SPRING_F5 supports the following 24 languages:
|
|
|
|
| 89 |
|
| 90 |
**SPRING_F5** is a multilingual text-to-speech (TTS) model based on **F5-TTS**, fine-tuned to support **23 Indian Language & English**.
|
| 91 |
|
|
|
|
|
|
|
| 92 |
## Supported Languages
|
| 93 |
|
| 94 |
SPRING_F5 supports the following 24 languages:
|