DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

AffectSpeech: A Large-Scale Emotional Speech Dataset with Fine-Grained Textual Descriptions for Speech Emotion Captioning and Synthesis

A framework for efficient model inference with omni-modality models

🎬 卡卡字幕助手 | VideoCaptioner - 基于 LLM 的智能字幕助手 - 视频字幕生成、断句、校正、字幕翻译全流程处理！- A powered tool for easy and efficient video subtitling.

Common Voice is part of Mozilla's initiative to help teach machines how real people speak.

Edit Banana: A framework for converting statistical formats into editable.

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

[TACL'26] VoiceBench: Benchmarking LLM-Based Voice Assistants

Unified Speech Language Model for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"(ICLR 2024)

本科华五，曾赴美qs50读博，某兄弟院校副教授，校园门卫亭女性主理人，为防止炸号的备份平台，是本人。

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

Reference-aware automatic speech evaluation toolkit

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)

[ACL 2026]

⚡ Clash for Lab 是为实验室环境设计的科学上网工具，无需sudo权限，优雅地一键式脚本安装

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.