A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
APACHE-2.0 License
End-to-End Speech Processing Toolkit
Neural building blocks for speaker diarization: speech activity detection, speaker change detecti...
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training w...
ICASSP 2023 Accepted
An Open Source text-to-speech system built by inverting Whisper.
A PyTorch implementation of Location-Relative Attention Mechanisms For Robust Long-Form Speech Sy...
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
Kaggle | 1st place solution for Freesound Audio Tagging 2019
Unofficial PyTorch implementation of Google AI's VoiceFilter system
SEGAN pytorch implementation https://arxiv.org/abs/1703.09452
Pytorch实现的流式与非流式的自动语音识别框架,同时兼容在线和离线识别,目前支持Conformer、Squeezeformer、DeepSpeech2模型,支持多种数据增强方法。
The Pytorch implementation of sound classification supports EcapaTdnn, PANNS, TDNN, Res2Net, ResN...