whisper-preprocess SKILL.md skillA
whisper-preprocess from j0ruge/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add j0ruge/skills/whisper-preprocess@v1.1.0Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- j0ruge/skills
- Path
plugins/whisper-preprocess/skills/whisper-preprocess/SKILL.md- Versions recorded
- 3
- Latest version
- v1.1.0, committed Sep 3, 2026
- First version recorded
- May 30, 2026
- Size
- 17,459 bytes
- Repository stars
- 13
- License
- none declared
Audio preprocessing and transcription with ffmpeg + OpenAI Whisper, fully offline — extraction, silence removal, voice enhancement, segmentation, then transcription. Handles MKV, MP4, WAV, M4A and other media. Triggers — transcribe audio or video, lecture/meeting/podcast/interview transcript, speech-to-text, transcrição, Whisper, remove silence, improve audio before transcription, convert media to text.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Whisper Preprocess Pipeline You are setting up and running an audio preprocessing + transcription pipeline. This pipeline solves four critical Whisper problems: 1. **Hallucinations during silence** — Whisper invents text like "Obrigado", "E ai", "Subscribe" during quiet segments 2. **Hallucination cascade in long audio** — after the first hallucination, Whisper repeats it for the rest of the file 3. **Poor transcription from noisy audio** — background noise reduces accuracy 4. **Silent failures on Windows due to encoding** — the `whisper` CLI crashes when printing accented/CJK characters in a cp1252 console, producing empty `.txt` files with no clear error The pipeline runs **100% offline** when the Whisper model is already cached locally — only needs ffmpeg, Python, and the downloaded model. ## Critical lessons learned (from real-world testing) These are hard-won insights from iterating on a 2h13min lecture recording and a multilingual (PT+JA) meeting; each one names the failure it prevents: ### 1. No `afftdn` (FFT noise reduction) on the transcription path …
Read the whole file at its exact version.
How to install
mdr add j0ruge/skills/whisper-preprocess@sha256:2274e0bd5e424ed6The line at the top of this page pins the label v1.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ogz7ayvxeyrzrchu)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between May 30, 2026 and Sep 3, 2026, about one every 48 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-09-03 | 1647f39 | 17,459 B | A | view · diff |
| v1.0.1 | 2026-08-26 | f1e0931 | 16,949 B | A | view · diff |
| v1.0.0 | 2026-05-30 | 9a830cc | 17,115 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (17459 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
j0ruge/skills · 13 stars · license none declared · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ogz7ayvxeyrzrchu GET https://markdownregistry.com/api/v1/resolve?ref=j0ruge/skills/whisper-preprocess GET https://markdownregistry.com/api/v1/blob/2274e0bd5e424ed6697b707b3a1454eb4d90ab5ab792b74de858567a2a16fa84
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.