whisper
Recipe card from the charly-tools plugin (Images — the deployable catalog).
whisper – OpenAI Whisper STT
Section titled “whisper – OpenAI Whisper STT”Candy Properties
Section titled “Candy Properties”| Property | Value |
|---|---|
| Install files | charly.yml, pixi.toml |
| Depends | python, cuda, ffmpeg |
# box charly.yml — compose the candy as an inline list in the box bodymy-box: candy: base: fedora candy: [whisper]Used In Boxes
Section titled “Used In Boxes”Related Candies
Section titled “Related Candies”/charly-languages:python— Python runtime — required dependency/charly-distros:cuda— CUDA toolkit — required dependency/charly-selkies:ffmpeg— FFmpeg multimedia (nonfree codecs) — required dependency/charly-tools:sherpa-onnx— alternative STT engine (ONNX-based, lighter weight)
When to Use This Skill
Section titled “When to Use This Skill”Use when the user asks about:
- Speech-to-text in containers
- OpenAI Whisper setup
- Audio transcription with CUDA
- The
whispercandy
Related
Section titled “Related”/charly-image:layer— candy authoring reference (charly.ymlschema, plan-step verbs, service declarations)/charly-check:check— declarative testing (check:block,charly check box,charly check live)