dr-data
PhD, Physicist@HKU, entrepreneur, biohacker@42laboratory, hardware hacker & entrepreneurship educator in HK. Former HKU Court Member. Smart is the new sexy.
@3rdcollege Hong Kong and Singapore
dr-data's Stars
collabora/WhisperLive
A nearly-live implementation of OpenAI's Whisper.
lipku/LiveTalking
Real time interactive streaming digital human
supermemoryai/opensearch-ai
SearchGPT / Perplexity clone, but personalised for you.
Jungstershark/HelloTT
Hello TT is an AI-powered chatbot developed for the Temasek X SUTD Gen AI Hackathon 2024. It assists users in resolving issues by generating step-by-step guides based on textual information and screenshots. Leveraging GPT-3.5 and GPT-4-Vision models, Hello TT provides intuitive, accurate, and visually enhanced solutions.
Markeljan/crew
CrewAI powered agents with Bitcoin wallets.
Markeljan/web3sim
Generative UI for smart contracts
Markeljan/stxgpt
Write Clarity smart contracts using any programing language.
Markeljan/coingecko-ai
web3-gpt/web3gpt
Write and deploy smart contracts using natural language prompts.
Avadhkumar-geek/StudentAI_API
Avadhkumar-geek/StudentAI
StudentAI is an prompt-less AI chatbot app that uses OpenAI's large language model to help students learn more effectively. StudentAI can answer questions, provide explanations, and even generate creative content. This makes it a powerful tool for students of all ages and levels of learning.
KoljaB/RealtimeTTS
Converts text to speech in realtime
OvidijusParsiunas/deep-chat
Fully customizable AI chatbot component for your website
KoljaB/AIVoiceChat
Low latency ai companion voice talk in 60 lines of code using faster_whisper and elevenlabs input streaming
m-bain/whisperX
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
SYSTRAN/faster-whisper
Faster Whisper transcription with CTranslate2
KoljaB/RealtimeSTT
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
KoljaB/WhoSpeaks
Efficient approach to speaker diarization using voice characteristics extraction
KoljaB/ai_cli_tools
AI at your fingertips: powerful CLI tools for speech, text, and language processing
deepgram/self-hosted-resources
Official Deepgram resources for deploying Deepgram services in a self-hosted environment
leopoldpoldus/streamlit_whisper_transcription
Streamlit Audio Transcription with OPENAI's Whisper Ai: An interactive Streamlit app demonstrating real-time audio transcription using OPENAI's Whisper Ai.
modal-labs/quillman
A voice chat app
juanmc2005/diart
A python package to build AI-powered real-time audio applications
svpino/unstract-llmwhisperer-sample
svpino/ml.school
Machine Learning School
svpino/livekit-assistant
RVC-Boss/GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
intothevoid/rss2podcast
Parse, summarise and convert rss feeds into an audio podcast
AlejandroAkbal/Screenshot-API
Self hosted API to take screenshots of any website
lamm-mit/PDF2Audio