chore(docker): default to multilingual whisper small for STT#94
Merged
Conversation
The bundled whisper.cpp model was ggml-tiny.bin - technically multilingual but effectively English-grade, so German/Spanish voice notes transcribed poorly. The image now ships ggml-small.bin (466 MB), the multilingual small variant, which gives usable DE/EN/ES quality with no code changes (WHISPER_MODEL build arg default bumped, both compose configs and docs updated to match). Verified: whisper stage builds, model downloads, whisper-cli runs.
Deploying with
|
| Status | Name | Latest Commit | Preview URL | Updated (UTC) |
|---|---|---|---|---|
| ✅ Deployment successful! View logs |
odek | 9853339 | Commit Preview URL Branch Preview URL |
Jul 22 2026, 07:03 PM |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The bundled whisper.cpp model was
ggml-tiny.bin— technically multilingual but effectively English-grade, so German and Spanish voice notes transcribed poorly.Change (build-arg default only, no code):
docker/Dockerfile:ARG WHISPER_MODEL=tiny→small(shipsggml-small.bin, 466 MB, multilingual — explicitly notsmall.en)docker/config.restricted.json/config.godmode.json:transcription.model: "small"docker/README.md,docs/TELEGRAM.md: model path/name + multilingual noteVerified: whisper stage builds clean,
ggml-small.bin(466 MB) downloads,whisper-cliruns.Takes effect on the next image rebuild (
docker compose --profile telegram-restricted build odek-telegram-restrictedorup --build). Size note: image grows ~390 MB vs. tiny; RAM during transcription ~2 GB. For best-in-class multilingual accuracy later, the same one-line bump takesmedium— documented in the Dockerfile comment.