Lists (19)
acleda
AI
ASR
backend
Data Engineer
Data Scientist
ecommerce
face_recognition
frontend
khmerllm
khmernlp
mobile
OCR
Recommendation System
server
Sigmoid_learning
sigmoid-shop
Tools
Tools for development workflowTTS
Stars
GUI for a Vocal Remover that uses Deep Neural Networks.
Fast inference engine for Transformer models
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
PostgreSQL monitoring and backups (with UI and self hosted)
Faster Whisper transcription with CTranslate2
Robust Speech Recognition via Large-Scale Weak Supervision
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
A complement to pgvector for high performance, cost efficient vector search on large workloads.
Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.
This repository is the official implementation of our paper "Preserving Fairness Generalization in Deepfake Detection", which has been accepted by CVPR 2024.
[EMNLP Main '25] LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation
CrateDB is a distributed and scalable SQL database for storing and analyzing massive amounts of data in near real-time, even with complex queries. It is PostgreSQL-compatible, and based on Lucene.
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Bringing shadcn/ui to React Native. Beautifully crafted components with Nativewind, open source, and almost as easy to use.
Images to inference with no labeling (use foundation models to train supervised models).
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
An open source implementation of CLIP.
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
OpenOCR: A general OCR system with accuracy and efficiency. Supporting 24 Scene Text Recognition methods trained from scratch on large-scale real datasets, and will continue to add the latest methods.
Script to download YouTube videos and convert them to MP3 format using multiple CPU cores
All plugins and configurations of neovim to supercharge vim user