Lists (1)
Stars
🚀 JIT Implementation: Code That Writes Itself
EyePy is an eye tracking library easily implementable in your projcets
Simple AI Templates on Live Video
Efficient Triton Kernels for LLM Training
A community-maintained Python framework for creating mathematical animations.
A fast and lightweight pure Python library for splitting text into semantically meaningful chunks.
A throughput-oriented high-performance serving framework for LLMs
Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
A web novel translator using OpenAI's GPT AI models
DSPy: The framework for programming—not prompting—foundation models
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
FastAPI with async/await background tasks (ARQ, SAQ, FastStream, Celery) + Prometheus + Grafana
A prompting enhancement library for transformers-type text embedding systems
Create and modify Word documents with Python
Transformation spoken text to written text
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
OpenUI let's you describe UI using your imagination, then see it rendered live.
Python - NSW package for Vietnamese: Normalization system to convert numbers, abbreviations, and words that cannot be pronounced into syllables
The YouTube Text-To-Speech dataset is comprised of waveform audio extracted from YouTube videos alongside their English transcriptions
Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)