vshanyiao

Emotional-Speech-Data

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

B-Llama3-o

B-Llama3o a llama3 with Vision Audio and Audio understanding as well as text and Audio and Animation Data output.

gpt_sovits_infer_with_emotion

基于中文文本情绪分析自动切换参考音频的 GPT-SoVITS 推理 Demo

ChatTTS

A generative speech model for daily dialogue.

metavoice-src

Foundational model for human-like, expressive TTS

agents

Build real-time multimodal AI applications 🤖🎙️📹

Wav2Vec2FBX

Recognize speech from an audio file and convert it into animation FBX

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

GPT-SoVITS

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

mPLUG-DocOwl

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

RGB

vocode-core

🤖 Build voice-based LLM agents. Modular + open source.

speechbrain

A PyTorch-based Speech Toolkit

pydub

Manipulate audio with a simple and easy high level interface

xtts-streaming-server

AceGPT

TTS

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

WhisperSpeech

An Open Source text-to-speech system built by inverting Whisper.

kenlm

KenLM: Faster and Smaller Language Model Queries

fastText

Library for fast text representation and classification.

sglang

SGLang is yet another fast serving framework for large language models and vision language models.

wetts

Production First and Production Ready End-to-End Text-to-Speech Toolkit

vits_chinese

Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

emotional-vits

无需情感标注的情感可控语音合成模型，基于VITS

everyone-can-use-english

人人都能用英语

silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

LWM

magvit2-pytorch

Implementation of MagViT2 Tokenizer in Pytorch

magvit

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

dingdang-robot

🤖 叮当是一款可以工作在 Raspberry Pi 上的中文语音对话机器人/智能音箱项目。