.svg){kind=icon}
Malaya-Speech is a Speech-Toolkit library for bahasa Malaysia, powered by Deep Learning Tensorflow.
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 3.6.0 and above and Tensorflow 1.15.0 and above are supported.
We recommend to use virtualenv for development. All examples tested on Tensorflow version 1.15.4, 1.15.5, 2.4.1 and 2.5.
Features
- Age Detection, detect age in speech using Finetuned Speaker Vector.
- Speaker Diarization, diarizing speakers using Pretrained Speaker Vector.
- Emotion Detection, detect emotions in speech using Finetuned Speaker Vector.
- Force Alignment, generate a time-aligned transcription of an audio file using RNNT.
- Gender Detection, detect genders in speech using Finetuned Speaker Vector.
- Language Detection, detect hyperlocal languages in speech using Finetuned Speaker Vector.
- Multispeaker Separation, Multispeaker separation using FastSep on 8k Wav.
- Noise Reduction, reduce multilevel noises using STFT UNET.
- Speaker Change, detect changing speakers using Finetuned Speaker Vector.
- Speaker overlap, detect overlap speakers using Finetuned Speaker Vector.
- Speaker Vector, calculate similarity between speakers using Pretrained Speaker Vector.
- Speech Enhancement, enhance voice activities using Waveform UNET.
- SpeechSplit Conversion, detailed speaking style conversion by disentangling speech into content, timbre, rhythm and pitch using PyWorld and PySPTK.
- Speech-to-Text, End-to-End Speech to Text for Malay, Mixed (Malay, Singlish and Mandarin) and Singlish using RNNT and Wav2Vec2 CTC.
- Super Resolution, Super Resolution 4x for Waveform.
- Text-to-Speech, Text to Speech for Malay and Singlish using Tacotron2, FastSpeech2 and FastPitch.
- Vocoder, convert Mel to Waveform using MelGAN, Multiband MelGAN and Universal MelGAN Vocoder.
- Voice Activity Detection, detect voice activities using Finetuned Speaker Vector.
- Voice Conversion, Many-to-One, One-to-Many, Many-to-Many, and Zero-shot Voice Conversion.
- Hybrid 8-bit Quantization, provide hybrid 8-bit quantization for all models to reduce inference time up to 2x and model size up to 4x.
Pretrained Models
Malaya-Speech also released pretrained models, simply check at malaya-speech/pretrained-model
- Wave UNET, Multi-Scale Neural Network for End-to-End Audio Source Separation, https://arxiv.org/abs/1806.03185
- Wave ResNet UNET, added ResNet style into Wave UNET, no paper produced.
- Wave ResNext UNET, added ResNext style into Wave UNET, no paper produced.
- Deep Speaker, An End-to-End Neural Speaker Embedding System, https://arxiv.org/pdf/1705.02304.pdf
- SpeakerNet, 1D Depth-wise Separable Convolutional Network for Text-Independent Speaker Recognition and Verification, https://arxiv.org/abs/2010.12653
- VGGVox, a large-scale speaker identification dataset, https://arxiv.org/pdf/1706.08612.pdf
- GhostVLAD, Utterance-level Aggregation For Speaker Recognition In The Wild, https://arxiv.org/abs/1902.10107
- Conformer, Convolution-augmented Transformer for Speech Recognition, https://arxiv.org/abs/2005.08100
- ALConformer, A lite Conformer, no paper produced.
- Jasper, An End-to-End Convolutional Neural Acoustic Model, https://arxiv.org/abs/1904.03288
- Tacotron2, Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions, https://arxiv.org/abs/1712.05884
- FastSpeech2, Fast and High-Quality End-to-End Text to Speech, https://arxiv.org/abs/2006.04558
- MelGAN, Generative Adversarial Networks for Conditional Waveform Synthesis, https://arxiv.org/abs/1910.06711
- Multi-band MelGAN, Faster Waveform Generation for High-Quality Text-to-Speech, https://arxiv.org/abs/2005.05106
- SRGAN, Modified version of SRGAN to do 1D Convolution, Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network, https://arxiv.org/abs/1609.04802
- Speech Enhancement UNET, https://github.com/haoxiangsnr/Wave-U-Net-for-Speech-Enhancement
- Speech Enhancement ResNet UNET, Added ResNet style into Speech Enhancement UNET, no paper produced.
- Speech Enhancement ResNext UNET, Added ResNext style into Speech Enhancement UNET, no paper produced.
- Universal MelGAN, Universal MelGAN: A Robust Neural Vocoder for High-Fidelity Waveform Generation in Multiple Domains, https://arxiv.org/abs/2011.09631
- FastVC, Faster and Accurate Voice Conversion using Transformer, no paper produced.
- FastSep, Faster and Accurate Speech Separation using Transformer, no paper produced.
- wav2vec 2.0, A Framework for Self-Supervised Learning of Speech Representations, https://arxiv.org/abs/2006.11477
- FastSpeechSplit, Unsupervised Speech Decomposition Via Triple Information Bottleneck using Transformer, no paper produced.
- Sepformer, Attention is All You Need in Speech Separation, https://arxiv.org/abs/2010.13154
- FastSpeechSplit, Faster and Accurate Speech Split Conversion using Transformer, no paper produced.
- HuBERT, Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units, https://arxiv.org/pdf/2106.07447v1.pdf
- FastPitch, Parallel Text-to-speech with Pitch Prediction, https://arxiv.org/abs/2006.06873
- GlowTTS, A Generative Flow for Text-to-Speech via Monotonic Alignment Search, https://arxiv.org/abs/2005.11129
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.
31 Aug 16, 2021
247 Jan 5, 2023
186 Dec 24, 2022
483 Jan 4, 2023
922 Dec 31, 2022
247 Dec 26, 2022
29 Oct 16, 2022
10 Oct 13, 2022
193 Jan 4, 2023
7 Dec 13, 2022
6k Dec 31, 2022
35 Oct 18, 2021
48 Dec 14, 2022
84 Dec 27, 2022
1.6k Dec 27, 2022
408 Dec 29, 2022
10 Jul 01, 2022
3 Aug 25, 2022
40 Nov 10, 2022
82 Dec 19, 2022
1 Oct 18, 2021
1 Mar 21, 2022
16 Nov 12, 2022
2 May 26, 2022
3 Nov 27, 2022
1 Jan 16, 2022
138 Dec 27, 2022
0 Oct 21, 2021
8 Dec 10, 2022