Malaya-Speech is a Speech-Toolkit library for Malaysian language, powered by PyTorch.

Stable released documentation is available at https://malaya-speech.readthedocs.io/en/stable/

$ pip install malaya-speech

It will automatically install all dependencies except for PyTorch. So you can choose your own PyTorch CPU / GPU version.

Only Python >= 3.6.0, and PyTorch >= 1.13 are supported.

If you are a Windows user, make sure read https://malaya.readthedocs.io/en/latest/running-on-windows.html

Install from master branch,

$ pip install git+https://github.com/mesolitica/malaya-speech.git

We recommend to use virtualenv for development.

While development released documentation is available at https://malaya-speech.readthedocs.io/en/latest/

Malaya-Speech also released Malaysian speech pretrained models, simply check at https://huggingface.co/mesolitica

If you use our software for research, please cite:

@misc{Malaya-Speech, Speech-Toolkit library for Malaysian language, powered by PyTorch,
  author = {Husein, Zolkepli},
  title = {Malaya-Speech},
  year = {2020},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/mesolitica/malaya-speech}}
}

Thanks to,

1. KeyReply for private V100s cloud.

2. Nvidia for Azure credit.

3. Tensorflow Research Cloud for free TPUs access.