On AI Lounge since Nov 2026
Dima Statz
Member #4,506DeveloperL2Software Engineer, Independed
Author whisper-flow , whipser-code, fluent-b, flattr, bendi-go, etc
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×3Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 3 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×3Featured
Shipper ×2Projects on your profile.How: Added 5 projects to their profile
Shipper×2
No posts yet
Dima Statz hasn't posted yet.
Pinned projects
Deep-Signal is an open-source framework that applies deep learning to analyze and interpret audio and signal data at scale. It combines traditional signal processing with modern AI to detect patterns, classify events, and uncover anomalies. Built for engineers and data scientists.
apache-sparkopenai-whisperspeech-to-text
EMA: AI Engineering Manager Assistant - is an open-source toolkit designed to supercharge Engineering Managers by automating the high-friction, recurring workflows that consume the work week. Built to run with Claude Code, EMA provides a suite of AI-assisted patterns to handle everything from technical alignment to team health.
flatr is a Python library that takes any GitHub repository and creates a flat Markdown (.md) file containing the entire codebase and documentation. It is designed to make codebases easier to feed into LLMs for tasks like code explanation, summarization, and interactive documentation.
codeexploration
geminillmpypi-package
An AI-driven platform that generates engaging, educational, and age-appropriate podcasts for children aged 6–12. By combining Large Language Models (LLMs), high-quality Text-to-Speech (TTS) technology, and curated educational content (e.g., Wikipedia), MindQuest transforms verified facts into fun, interactive audio stories.
Real-time voice dictation for VS Code, powered by local Whisper. Biases transcription with your workspace symbols so it spells useMemo right, and adapts to whether you're dictating a comment, a commit message, or a prompt.
Whisper-Flow is a framework designed to enable real-time transcription of audio content using OpenAI’s Whisper model. Rather than processing entire files after upload (“batch mode”), Whisper-Flow accepts a continuous stream of audio chunks and produces incremental transcripts immediately.
pypi-package
pythonspeech-to-texttranscription
whisper
About
Dima Statz works as a software engineer at Independed in Cape Town, South Africa. Known for open-source work, Dima built whisper-flow, a Python framework that transcribes streamed audio with OpenAI's Whisper model, and flatr, a tool that packs a GitHub repository into one Markdown file for language models. Recent projects include deep-signal, which applies deep learning to audio and signal data, and EMA, an assistant toolkit for engineering managers that runs with Claude Code.
Stack
Experience
Director of Engineering · Salesforce
Y
Software Architect · Yahoo
C
Software Engineer · Cisco
C
Engineering Manager · Clicktale
TI
Software Engineer · Top Image Systems
M
Software Engineer · Microsoft
ES
Software Engineer · Elbit Systems Ltd
TO
Operating Systems course tutor · The Open University of Israel
