为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Easily train a good VC model with voice data <= 10 mins!

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

zero-shot voice conversion & singing voice conversion, with real-time support

TorchCFM: a Conditional Flow Matching library

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion

[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

Official implementation of Meta-StyleSpeech and StyleSpeech

A diffusion-based cross-lingual voice conversion model, as my bachelor's thesis

Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion

An implementation of deep-voice-conversion using pytorch

Analysis of XLS-R for Speech Quality Assessment