✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM

Blind Source Separation and Dereverberation

Complex Neural Beamformer

Easy to use Beamformers for multi-channel speech separation/enhancement

simple delaysum, MVDR and CGMM-MVDR

基于深度学习的声学回声消除基线代码

音频标注工具

End-To-End Deep Learning-based Adaptation Control for Linear Acoustic Echo Cancellation

Python library for Room Impulse Response (RIR) simulation with GPU acceleration

Official PyTorch implementation of BigVGAN (ICLR 2023)

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。

Faster Whisper transcription with CTranslate2

A high-resolution direction-of-arrival finding algorithm relying on finite rate of innovation sampling with a robust reconstruction algorithm.

unofficial vits2-TTS implementation in pytorch

partitioned block based frequency domain Kalman filter

Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva

This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

GeneFace: Generalized and High-Fidelity 3D Talking Face Synthesis; ICLR 2023; Official code

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

Acoustic Echo Cancellation with Nerual Kalman Filtering

Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.