Native End-to-End Full-Duplex Spoken Language Model

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

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…

A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp/pp.

Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.

Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

Official code for our paper, "LoRA-Pro: Are Low-Rank Adapters Properly Optimized? "

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

We Speech Transcript based on LLM, in 300 lines of code.

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Speech, Language, Audio, Music Processing with Large Language Model

Multilingual Voice Understanding Model

Prompting Large Language Models with Audio for General-Purpose Speech Summarization

ChatTTS is a generative speech model for daily dialogue.

Awesome speech/audio LLMs, representation learning, and codec models

⭐️ Markdown 简历模版

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Open-source, accurate and easy-to-use video clipping tool | 开源、精准、方便的视频切片工具

A Native-PyTorch Library for LLM Fine-tuning

ncnn is a high-performance neural network inference framework optimized for the mobile platform

A ctc decoder for both online and offline asr model

A Fundamental End-to-End Speech Recognition Toolkit

汉字转拼音(pypinyin)

A playbook for systematically maximizing the performance of deep learning models.