Official implementation of "Separate Anything You Describe"

本项目使用了EcapaTdnn、ResNetSE、ERes2Net、CAM++等多种先进的声纹识别模型，同时本项目也支持了MelSpectrogram、Spectrogram、MFCC、Fbank等多种数据预处理方法

High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！

Speech recognition

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

Text-To-Speech for NotebookLM

Android下音视频对讲演示程序

an extremely simple tool for separating vocals and background music, completely localized for web operation, using 2stems/4stems/5stems models 这是一个极简的人声和背景音乐分离工具，本地化网页操作，无需连接外网

[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

An Open-source Streaming High-fidelity Neural Audio Codec

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Offline Speaker Diarization with SenseVoice by Sherpa ONNX.

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

一个超轻量级、可以在移动端实时运行的数字人模型

Indonesian speech/phoneme recognizer powered by Kaldi 2.0 (lhotse, icefall, sherpa).

Synchronized Translation for Videos. Video dubbing

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

GLM-4-Voice | 端到端中英语音对话模型

A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.

基于Pytorch的OCR工具库，支持常用的文字检测和识别算法

Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation implemented by Pytorch

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers

TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models (2024 ICASSP)

A 6-million Audio-Caption Paired Dataset Built with a LLMs and ALMs-based Automatic Pipeline

通过LLM进行进行字幕断句分割，处理和优化字幕文件，将自动语音识别（ASR）数据的分段合并与拆分，