tiny-voca-arabic
A compact CPU-oriented model trained from scratch using the tiny-voca architecture and an Arabic phonetic front end.
Specifications
- Released
- Nov 21, 2026
- Inputs
- Text
- Weights
- Open weights · Apache-2.0
- Task
- Speech synthesis
- Published capabilities
- A compact CPU-oriented model trained from scratch using the tiny-voca architecture and an Arabic phonetic front end.
- Model size
- 4.53M parameters
- Access
- Downloadable ONNX and PyTorch weights
- Result
- 24 kHz mono speech in Modern Standard Arabic
- Operating limits
- Includes one synthetic Modern Standard Arabic voice. The publisher reports about 200× real-time generation on two CPU threads.
- Sources
- Model weights · Additional documentation