very currency

Open Source framework for voice and multimodal conversational AI

Large-scale pretrained models for goal-directed dialog

Enforce the output format (JSON Schema, Regex etc) of a language model

4 bits quantization of LLaMA using GPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

A fast inference library for running LLMs locally on modern consumer-class GPUs

A guidance language for controlling large language models.

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Fuse ChatTTS with OpenVoice, upload a 10-second audio clip, and clone your personalized ChatTTS voice.

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

Python script that slices audio with silence detection

Music Source Separation Training Inference Webui, besides, we packed UVR together!

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

For GGUF support, see KoboldCPP: https://github.com/LostRuins/koboldcpp

LLM Frontend for Power Users.

This repository contains the code and data for the paper EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control by Haozhe Chen, Run Chen, and Julia Hirschberg.

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Foundational model for human-like, expressive TTS

Code and documentation to train Stanford's Alpaca models, and generate the data.

This is the GitHub page for publicly available emotional speech data.

官方推荐的 ChatTTS 资源汇总项目，整理了全网相关资源和常见问题 || Officially recommended ChatTTS resource collection project

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

repository for CharacterChat, a personalized social support system

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.