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

Spark-TTS Inference Code

Open-Source Frontier Voice AI

🤗 smolagents: a barebones library for agents that think in code.

DeepTalk: Towards Seamless and Smart Speech Interaction with Adaptive Modality-Specific MoE

✨✨[NeurIPS 2025] VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model

Fast and memory-efficient exact attention

[SLT2024] DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition

[ICASSP2024] One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models

[ICASSP2023] Joint Discriminator and Transfer Based Fast Domain Adaptation for End-to-End Speech Recognition

LUCY: Linguistic Understanding and Control Yielding Early Stage of Her

[MICCAI 2024] Can LLMs' Tuning Methods Work in Medical Multimodal Domain?

微信聊天记录年度报告

Fantastic Data Engineering for Large Language Models

✨✨Latest Advances on Multimodal Large Language Models

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Stable Diffusion web UI

大麦网抢票脚本

📚 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计

基于Qt编写的智能管家系统客户端，实现语音识别，按钮音效，摄像头采集。