Code for Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights

Arabic speech recognition, classification and text-to-speech.

An unofficial PyTorch implementation of the audio LM VALL-E

Implementation of TTS model based on NVIDIA P-Flow TTS Paper

Style-Controllable Zero-Shot Text to Speech Synthesizer based on VALL-E

A PyTorch implementation of "Robust Universal Neural Vocoding"

[IJCAI'23] Learning to Speak from Text for Low-Resource TTS

Unofficial implementation of NVIDIA P-Flow TTS paper

44100Hz日本語音源に対応させた unofficial vits2-TTS implementation in pytorchです。

Split Korean text into sentences using heuristic algorithm.

unofficial vits2-TTS implementation in pytorch

VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

Korean text normalization and language preparation package for LM in Kaldi-based ASR system

Transformation spoken text to written text

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

The open source implementation of ChatGPT, Alpaca, Vicuna and RLHF Pipeline. 从0开始实现一个ChatGPT.

KSS: Korean String processing Suite

PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor

This is the implementation of our Interspeech 2020 paper "Converting anyone's emotion: towards speaker-independent emotional voice conversion".

Seq2Seq model implemented with pytorch, using Copy Mechanism and Coverage Mechanism.

Korean BART

Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Prometheus community Helm charts

Bitnami Helm Charts

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis