Python 排行榜

Codellama Instruct OpenAi style api.

Self-hosted multitenant platform for AI agents and Telegram bots with event-driven architecture

BackdoorMBTI is an open source project expanding the unimodal backdoor learning to a multimodal context. We hope that BackdoorMBTI can facilitate the analysis and development of backdoor defense methods within a multimodal context.

[ECCV 2026 Oral] Official Pytorch implementation for See & Sniff: Learning Visuo-Olfactory Representations

Code for "Dual-Level Adaptive Incongruity-Enhanced Model for Multimodal Sarcasm Detection".

[CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

[CVPR 2026 Main] MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation

Ask your video library anything — an AI agent that watches, reasons in a tool-use loop, and answers with playable clips and charts.

ComfyUI nodes for Qwen3-ASR (0.6B/1.7B) and ForcedAligner. Supports high-accuracy ASR and language identification for 52 languages/dialects, including 22 Chinese dialects and various English accents. Features word-level timestamps, long audio transcription, and VRAM-optimized inference.

Self-hosted voice assistant. Speak to your computer: it answers aloud, types your dictation, and operates your apps.

A lightweight library for normalizing speech transcripts before computing WER

speech to text gui for different (e.g. Whisper, Voxtral) models and backends, including whisper.cpp, crispasar, mlx-whisper, faster-whisper, ctranslate2; applies pyannote for diarization

VideoNote：视频链接 → 结构化笔记。理解画面/弹幕/评论；支持主流平台；工具解耦；多格式导出。

MediBeng Whisper Tiny improves doctor-patient transcription by training the Whisper Tiny model to translate mixed Bengali-English speech into English, making it easier for analysis, record-keeping, and using AI in healthcare.

Convert images or audio files to plain text on the command line

Effortless Push-to-Talk Transcription, Anywhere.

基于 SenseVoice 的 Windows 本地语音转文字工具，支持 OpenAI 格式 API 润色，低延迟，高精度。

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

A REST API for vLLM, production ready

Open-source local implementation of MiniMax H3 Context-IR. Turn simple prompts into structured, validated H3 video briefs.