🚀🚀🚀 A collection of some awesome public YOLO object detection series projects and the related object detection datasets.

A curated list of open-source projects related to DeepSeek Coder

AGI's query engine - Platform for building AI that can learn and answer questions over federated data.

Fully open reproduction of DeepSeek-R1

OpenAI API compatible proxy for NVIDIA Triton Inference Server

Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC…

A curated list of awesome ClickHouse software.

百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，时延低至800ms，低配置也可运行，支持打断

All-in-one infrastructure for search, recommendations, RAG, and analytics offered via API

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

A Lightweight Recommendation System

A pattern for an always on AI Assistant powered by Deepseek-V3, RealtimeSTT, and Typer for engineering

An extremely fast Python package and project manager, written in Rust.

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.

API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition, and speaker verification.

Multilingual Voice Understanding Model

中文翻译的 Hands-On-Large-Language-Models (hands-on-llms)，动手学习大模型

Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, Du…

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

AI 实战 · 微信话题订阅阅读器 - 支持订阅管理、即时刷新、阅读计数、本地缓存等等。

Faster Whisper transcription with CTranslate2

A high-throughput and memory-efficient inference and serving engine for LLMs

🚀🚀 「大模型」3小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 3 hours!

[WIP] Scripts for fine-tuning Whisper

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deplo…