Index
All Articles
Everything published here, newest first.
105 articles · Page 3 of 11
23 Cheshvan 5787
Proofed: could a speech model proofread its own transcript?
An idea in development: fine-tune Parakeet on cleanup alone, so dictation comes out without fillers, with digits and paragraphs, in one pass and with no LLM afterwards. Research done, data being recorded.
23 Cheshvan 5787 Update
Update: a 32 MB model for ASR paragraph breaks
MiniLM-L12-ASR-Paragraph-Breaks replaces my Gemma 3 270M paragraph model: break F1 0.85 against 0.78, 32 MB instead of 437 MB, and it cannot change a word of the transcript.
23 Cheshvan 5787
Agent Task Break Detector: knowing when to start a fresh session
A small ModernBERT model that checks every message in an AI agent session and says whether it is a new task a fresh session could handle. Runs locally on CPU; v0.1, trained on synthetic data.
22 Cheshvan 5787
A Claude Code transcription plugin that replaced five of my projects
Transcription Pipeline is a public Claude Code plugin that turns voice notes and calls into transcripts, specs, minutes and PDFs in eight stages. It replaced two plugins and three MCP servers, and was specified in a voice note it then transcribed.
16 Cheshvan 5787
My home AI gateway, v5: skills ate the MCP servers
Version five of my home AI gateway: skills overtook MCP servers, and one index now serves skills and tools.
16 Cheshvan 5787
Using AI to decide my vote in Israel's 2026 election
How I turned a 42-minute voice note into an AI vote decision for Israel's 2026 election: the method in diagrams, my result, and a step-by-step guide to doing it yourself with any AI chat app. No list has a real tenant-protection policy.
11 Cheshvan 5787
Forecasting Israel's election for two cents: decision models vs the markets
Two decision models answered 39 questions on Israel's 27 October election from a frozen pack of polls, lists and news, with and without market prices. It cost $0.016, and adding market prices flipped the forecast.
11 Cheshvan 5787
I had a conversation with my own voice clone
I fine-tuned a text-to-speech model on 88 minutes of my voice, then had a ten-minute conversation with it. My lines are real phone recordings; its lines are generated. Listen, and see how it was made.
11 Cheshvan 5787
The Linux mic slider lies: Mic Monitor shows the real gain
On Linux, the microphone volume slider is not your mic's analog gain: mine was 60 dB out. Mic Monitor is a KDE Plasma tray app that shows the real gain in dB, clipping and noise floor, tuned for dictation and speech recognition.
10 Cheshvan 5787
Adding paragraph breaks to speech-to-text output with Gemma 3 270M
A Gemma 3 270M fine-tune that adds paragraph breaks to flat speech-to-text output and changes nothing else. Small enough for on-device use, with an ONNX export. Break F1 0.78 on 26 held-out memos.