Instructions to use azeddinShr/Spark-TTS-Arabic-Complete with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use azeddinShr/Spark-TTS-Arabic-Complete with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="azeddinShr/Spark-TTS-Arabic-Complete")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("azeddinShr/Spark-TTS-Arabic-Complete", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -61,6 +61,8 @@ Can be further fine-tuned for:
|
|
| 61 |
- Languages other than Arabic
|
| 62 |
- Singing or non-speech audio generation
|
| 63 |
|
|
|
|
|
|
|
| 64 |
## 🚀 How to Use
|
| 65 |
|
| 66 |
### Installation
|
|
@@ -85,7 +87,6 @@ model_dir = snapshot_download(
|
|
| 85 |
local_dir="./arabic_model"
|
| 86 |
)
|
| 87 |
```
|
| 88 |
-
**Very Important Note:** This model requires the official Spark-TTS repository for inference. The model files alone are not sufficient - you must clone the Spark-TTS repo and use their inference pipeline.
|
| 89 |
|
| 90 |
### Setup Inference Environment
|
| 91 |
```python
|
|
|
|
| 61 |
- Languages other than Arabic
|
| 62 |
- Singing or non-speech audio generation
|
| 63 |
|
| 64 |
+
**Very Important Note:** This model requires the official Spark-TTS repository for inference. The model files alone are not sufficient - you must clone the Spark-TTS repo and use their inference pipeline.
|
| 65 |
+
|
| 66 |
## 🚀 How to Use
|
| 67 |
|
| 68 |
### Installation
|
|
|
|
| 87 |
local_dir="./arabic_model"
|
| 88 |
)
|
| 89 |
```
|
|
|
|
| 90 |
|
| 91 |
### Setup Inference Environment
|
| 92 |
```python
|