Local pipeline: Silero VAD + Whisper + Gemma 8B in Ollama for video extraction
gregmushen · x · 2026-10-09
The author details the pipeline: Silero VAD v5.1.2 removes silent segments before transcription so Whisper-Large-v3-turbo doesn't hallucinate during silence; Gemma (8B, Q4KM) running in Ollama 0.20.0 reads the transcript and, with some code to validate items, pulls out real repairs, then locates the video frames where each was discussed, picking the best of 6 candidate frames. A reproducible fully-local video-to-structured-data recipe.
More from coding & agent
- Swapping harness lifts GPT-5.6 repo migration from 6.5% to 31%, paper finds — omarsar0 · 2026-10-09
- He replaced a 17-step agent prompt checklist with a 1976 Unix Makefile — 140+ tickets without drift — RandalSchwartz · 2026-10-09
- Developer builds wildfire analysis tool with Opus 5.5: fire progression and hot spot tracking — natesiggard · 2026-10-09
- Subagent-as-a-service: betting on 'expert' agents like Harvey as tool calls for vertical AI — nbaschez · 2026-10-09
- WebMCP Debate: LLM Agents Skip Ads, Putting Ad-Based Business Models at Risk — ConnectRub4818 · 2026-10-09
- At first Grok Bot Meetup, audience-voted idea becomes a 139-marker map app in ~10 minutes — pswider · 2026-10-09