Fun-ASR-Nano-2512官方发布的仓库内容有点多，部署起来坑也比较多，本项目提供一个简化的部署方案。

GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters

End-to-end realtime stack for connecting humans and AI

Train your own speech AI model from scratch

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

A toolkit for speaker diarization.

A C++ standalone library for machine learning

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

🦜🔗 The platform for reliable agents.

FlashInfer: Kernel Library for LLM Serving

A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.

An audio reader & writer built on top of PyAV

Causal streaming adaptation of OpenAI Whisper for real-time transcription on small audio chunks.

FireRedChat pVAD plugin for LiveKit Agents

VoiceBench: Benchmarking LLM-Based Voice Assistants

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

A Massive Contextual Speech Recognition Benchmark.

An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement

cuML - RAPIDS Machine Learning Library

Official PyTorch inference code for the Interspeech 2025 paper: Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders

In-car multi-channel speech transcription system of AISHELL-5.

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

Language Technology Platform

ICLR 2025

Python tool for converting files and office documents to Markdown.

Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.

torchview: visualize pytorch models