logo

Pypi version Python3 version MIT License


Malaya-Speech is a Speech-Toolkit library for bahasa Malaysia, powered by Deep Learning Tensorflow. We maintain it at separate repository, https://github.com/huseinzol05/malaya-speech

Documentation

Proper documentation is available at https://malaya-speech.readthedocs.io/

Installing from the PyPI

CPU version

$ pip install malaya-speech

GPU version

$ pip install malaya-speech-gpu

Only Python 3.6.x and above and Tensorflow 1.10 and above but not 2.0 are supported.

Features

  • Age Detection, detect age in speech using Finetuned Speaker Vector Malaya-Speech models.

  • Speaker Diarization, diarizing speakers using Pretrained Speaker Vector Malaya-Speech models.

  • Emotion Detection, detect emotions in speech using Finetuned Speaker Vector Malaya-Speech models.

  • Gender Detection, detect genders in speech using Finetuned Speaker Vector Malaya-Speech models.

  • Language Detection, detect hyperlocal languages in speech using Finetuned Speaker Vector Malaya-Speech models.

  • Noise Reduction, reduce multilevel noises using Pretrained STFT UNET Malaya-Speech models.

  • Speaker Change, detect changing speakers using Finetuned Speaker Vector Malaya-Speech models.

  • Speaker overlap, detect overlap speakers using Finetuned Speaker Vector Malaya-Speech models.

  • Speaker Vector, calculate similarity between speakers using Pretrained Malaya-Speech models.

  • Speech Enhancement, enhance voice activities using Pretrained Waveform UNET Malaya-Speech models.

  • Speech-to-Text, End-to-End Speech to Text using Pretrained CTC and RNN Transducer Malaya-Speech models.

  • Super Resolution, Super Resolution 4x using Pretrained Super Resolution Malaya-Speech models.

  • Text-to-Speech, using Pretrained Tacotron2 and FastSpeech2 Malaya-Speech models.

  • Vocoder, convert Mel to Waveform using Pretrained MelGAN and Multiband MelGAN Vocoder Malaya-Speech models.

  • Voice Activity Detection, detect voice activities using Finetuned Speaker Vector Malaya-Speech models.

Pretrained Models

Malaya-Speech also released pretrained models, simply check at malaya-speech/pretrained-model

References

If you use our software for research, please cite:

@misc{Malaya, Speech-Toolkit library for bahasa Malaysia, powered by Deep Learning Tensorflow,
  author = {Husein, Zolkepli},
  title = {Malaya-Speech},
  year = {2020},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/huseinzol05/malaya-speech}}
}

Acknowledgement

Thanks to KeyReply for sponsoring private cloud to train Malaya-Speech models, without it, this library will collapse entirely.

logo