Claude Code Snapshot for Research. All original source code is the property of Anthropic.

Spark-TTS Inference Code

Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.

Text to speech alignment using CTC forced alignment

Train the next generation of TTS systems.

The Open Source Code of UniAudio

翻墙-科学上网、免费科学上网、免费翻墙、油管youtube、fanqiang、VPN、一键翻墙浏览器，vps一键搭建翻墙服务器脚本/教程，免费shadowsocks/ss/ssr/v2ray/goflyway账号/节点，免费自由上网、翻墙梯子，电脑、手机、iOS、安卓、windows、Mac、Linux、路由器翻墙、科学上网

Source code for: Expressive Speech-driven Facial Animation with controllable emotions

Core Engine of Singing Voice Conversion & Singing Voice Clone

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

PyTorch Implementation of GenerSpeech (NeurIPS'22): a text-to-speech model towards zero-shot style transfer of OOD custom voice.

支持多协议多用户的 xray 面板

Official implementation of the source-filter HiFiGAN vocoder

A latent text-to-image diffusion model

PyTorch Implementation of ProDiff (ACM-MM'22) with a Extremely-Fast diffusion speech synthesis pipeline

Mandarin Grapheme-to-Phoneme Converter. 中文轉注音或拼音

Official implementation of SawSing (ISMIR'22)

Simple text to phones converter for multiple languages

Neural network-based singing voice synthesis library for research

Use VITS and Opencpop to develop singing voice synthesis; Maybe it will VISinger.

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code