Harras3
I am currently pursuing BSCS from FAST NUCES ISB. I have been learning ML from past 2 years and now working on LLM based apps for my own learning.
National University Of Computer And Emerging Sciences
Pinned Repositories
-SATechnicalOnboarding
abstract_vectordb
Trying to make generic code that can cater all vector databases
Build-On-Core
This repository showcases projects and solutions developed during hackathons, workshops, and related events and other Builder Programs.
data-science
deep-learning
distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Enterprise-Grade-RAG
This is a RAG based chatbot in which semantic cache and guardrails have been incorporated.
Google-Hackathon
Multithreaded-dummy-Neural-Network
This is code for a multithreaded dummy neural network in C++
unhallucinated-faster-whisper
'unhallucinated-faster-whisper,' a powerful enhancement built on the faster-whisper framework for audio transcription.
Harras3's Repositories
Harras3/Enterprise-Grade-RAG
This is a RAG based chatbot in which semantic cache and guardrails have been incorporated.
Harras3/unhallucinated-faster-whisper
'unhallucinated-faster-whisper,' a powerful enhancement built on the faster-whisper framework for audio transcription.
Harras3/abstract_vectordb
Trying to make generic code that can cater all vector databases
Harras3/Google-Hackathon
Harras3/-SATechnicalOnboarding
Harras3/Build-On-Core
This repository showcases projects and solutions developed during hackathons, workshops, and related events and other Builder Programs.
Harras3/data-science
Harras3/deep-learning
Harras3/distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Harras3/EduAssist
An educational web app in Next JS, TypeScript and Tailwind CSS.
Harras3/Multithreaded-dummy-Neural-Network
This is code for a multithreaded dummy neural network in C++
Harras3/faster-whisper
Faster Whisper transcription with CTranslate2
Harras3/genai-project
Harras3/Lending-dApp
Harras3/reviewing-a-pull-request
Harras3/udacity
Harras3/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Harras3/VoiceChat
Local Voice Chatting with an LLM using FOSS models on a consumer GPU