Claude Code 源码文档解析

分享AI Infra知识&代码练习：PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等

Plug-and-play streaming semantic VAD for real-time full-duplex spoken dialogue systems.

Pre-training, SFT, DPO and GRPO for Text-to-Audio Generation

A SOTA Industrial-Grade Voice Activity Detection & Audio Event Detection, supporting 100+ languages, outperforming Silero-VAD, TEN-VAD, FunASR-VAD and WebRTC-VAD

Compute WER and SER for speech recognition evaluation

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…

Finetune Nemo parakeet ASR model with new language (support 8 bit optimizer). Experimental birwkv-fastconformer TDT for long-form ASR(8.5 hours in single pass).

Very fast, accurate speaker diarization

Nano vLLM

A demo-level low-latency, high-throughput inference engine for whisper

🐍📦 Ultra-fast Python package for calculating and analyzing the Word Error Rate (WER). Built for the scalable evaluation of speech and transcription accuracy.

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

Text-to-text alignment algorithm for speech recognition error analysis.

轻量级大语言模型MiniMind的源码解读，包含tokenizer、RoPE、MoE、KV Cache、pretraining、SFT、LoRA、DPO等完整流程

A python module to repair invalid JSON from LLMs

Open-Source Frontier Voice AI

Simultaneous speech-to-text models

MOSS-TTSD is a spoken dialogue generation model designed for expressive multi-speaker synthesis. It features long-context modeling, flexible speaker control, and multilingual support, while enablin…

Text-audio foundation model from Boson AI

Chinese voice corpus. 中文语音语料，语音更加清晰自然，包含8个开源数据集，3200个说话人，900小时语音，1300万字。

UTokyo-SaruLab MOS Prediction System

A Collection of Papers on Diffusion Language Models

Spark-TTS Inference Code

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

中文文本纠错数据集汇总