Python 排行榜

Code and dataset release for "PACS: A Dataset for Physical Audiovisual CommonSense Reasoning" (ECCV 2022)

[ICML'26] Toward Human-like Audio-Visual Intelligence of Omni-MLLMs

[ICLR 2026🔥] SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense

Local IAB Content Taxonomy Mapper (2.x → 3.0). Deterministic → fuzzy → optional embeddings. Exports OpenRTB & VAST-ready category IDs with vector attributes and SCD awareness.

Code and data for ACL 2024 paper on 'Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space'

Open Translator: Speech To Speech and Speech to text Translator with voice cloning and other cool features

[CVPR 2026] Official repo of UniM

Extract structured data from documents, images, audio, and video using LLMs in Python

This repo contains the original implementation of VAuLT, the Vision-and-Augmented-Language Transformer. We provide instructions to download some multimodal social-media datasets, and scripts to experiment with. VAuLT is a stack of Transformers, a LM like BERT that preprocesses the text input of ViLT

[IEEE TMM 2024] IGReg: Image-Geometry-Assisted Point Cloud Registration via Selective Correlation Fusion

A Comprehensive Speech Processing Algorithms Library for research and production use

Local inference server for Apple Silicon — hot-swaps MLX models (LLM, vision, embeddings, TTS, STT) via OpenAI API

benchmark for Speech-to-Intent engines

DiscordNPC lets you interact with ChatGPT through a Discord voice channel, enabling a natural conversation.

Listen4Me bot converts audio messages into text.

A small wrapper package around whisper-timestamped. Create force-aligned transcription TextGrids from raw audio!

Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted pieces (pjsua2 + whisper.cpp + Linphone). No paid telephony, no extra API key.

I'm sorry, Dave. I'm afraid I can't let that spam call through. — Local AI answering service with voice cloning, call recording, and sub-second latency. Runs entirely on your GPU. No cloud. No per-minute billing. Just HAL.

An OpenAI Compatible API which integrates LLM, Embedding and Reranker. 一个集成 LLM、Embedding 和 Reranker 的 OpenAI 兼容 API

Source code for the paper: Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention