An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.

🤗 R1-AQA Model: mispeech/r1-aqa

SALMONN family: A suite of advanced multi-modal LLMs

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Official code release for "Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency"

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

A Framework for Speech, Language, Audio, Music Processing with Large Language Model

[ECCV`24&ICLR`25] CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians

The best ChatGPT that $100 can buy.

We Speech Toolkit, LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages

TorchCFM: a Conditional Flow Matching library

Depth Anything 3

CUDA accelerated rasterization of gaussian splatting

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Train transformer language models with reinforcement learning.

🤗 R1-AQA Model: mispeech/r1-aqa

SALMONN family: A suite of advanced multi-modal LLMs

Update ASR paper everyday

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

A python package to build AI-powered real-time audio applications

Some comprehensive papers about speaker diarization

Tools for handling multimodal data in machine learning projects.

Tools for handling multimodal data in machine learning projects.

TorchCFM: a Conditional Flow Matching library

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.