Deezer source separation library including pretrained models.
- deezer
- python
- tensorflow
- audio-processing
91,851 visible repositories in the index
1–24 of 24 · Most stars
Deezer source separation library including pretrained models.
GUI for a Vocal Remover that uses Deep Neural Networks.
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
Markdown Presentations for Tech Conferences, Training, Developer Advocates, and Educators.
Drop-in replacement for Requests. Automatic HTTP/1.1, HTTP/2, and HTTP/3. WebSocket, and SSE included. WASI Supported.
VLX-Seek is an efficient VLM that grounds fine-grained visual targets with high precision in wild environments.
Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.
ELI5 — A Claude Code skill that explains anything to anyone: kids, managers, engineers, parents. Adapts tone, vocabulary, and analogies to match the audience.
[ECCV 2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.
Vocal Remover using Deep Neural Networks
Python reference implementation of The Update Framework (TUF)
Must-have resource for anyone who wants to experiment with and build on the OpenAI vision API 🔥
[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python package, using a variety of amazing pre-trained models (primarily from UVR)
Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.
Self-hosted control plane for TLS certificates, ready for 47-day certificates: issue, renew, discover, inventory and deploy them, and serve ACME for internal names and IPv4 addresses
Real-time and accurate open-vocabulary end-to-end object detection
RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs
This codebase demonstrates how to synthesize realistic 3D character animations given an arbitrary speech signal and a static character mesh.
A JupyterLab plugin to facilitate invocation of code formatters.
[CVPR 2025] Video Narration as Vocabulary & Video as Long Document
Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.