-
Codemonk, Elvago Technologies
- INDIA
- https://www.linkedin.com/in/abhishek-c-salian
- @ACSalian
Starred repositories
🌐 The Internet OS! Free, Open-Source, and Self-Hostable.
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
A Comprehensive Toolkit for High-Quality PDF Content Extraction
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
A modular graph-based Retrieval-Augmented Generation (RAG) system
Controllable and fast Text-to-Speech for over 7000 languages!
My-Voice Analysis is a Python library for the analysis of voice (simultaneous speech, high entropy) without the need of a transcription. It breaks utterances and detects syllable boundaries, fundam…
AI based emotions and english fluency checking from the input video..
Make YouTube Chapters from a downloaded Transcript
A classified list of meta learning papers based on realm.
A library for Bayesian neural network layers and uncertainty estimation in Deep Learning extending the core of PyTorch
Well-documented Python demonstrations for spatial data analytics, geostatistical and machine learning to support my courses.
OMG-LLaVA and OMG-Seg codebase [CVPR-24 and NeurIPS-24]
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Official code repository for the paper: "Neural Spline Fields for Burst Image Fusion and Layer Separation"
Reference implementation for DPO (Direct Preference Optimization)
A pytorch implementation for BPR (Bayesian Personalized Ranking).
WhisperPlus: Faster, Smarter, and More Capable 🚀
This is a background removing tool powered by InSPyReNet (ACCV 2022)
pix2tex: Using a ViT to convert images of equations into LaTeX code.
Understanding Deep Learning - Simon J.D. Prince