Huddle transcription is English-only: non-English speech (e.g. Korean) produces garbled transcripts

[baekchan-dev]

Summary

Huddle transcription produces garbled output for any non-English speech. The embedded STT model is hardcoded to an English-only model, with no language setting or override.

What happens

Speaking Korean in a huddle yields transcripts like:

"You know b H texture Isam an onoroso Chen."
"I to go to Tantaa"

The model force-decodes Korean audio into English tokens, so the output is unusable. English speech transcribes fine.

Root cause

The STT model is pinned to NVIDIA Parakeet TDT-CTC 110M English-only in desktop/src-tauri/src/huddle/models.rs:

• STT_MODEL_DIR_NAME: &str = "parakeet-tdt-ctc-110m-en" (models.rs:131)
• Download archive pinned to sherpa-onnx-nemo-parakeet_tdt_ctc_110m-en-36000-int8.tar.bz2 with a checksum (models.rs:125-128)

There is no language option, env override, or model-swap path — the loader only knows this one model.

Proposal

The embedded engine (sherpa-onnx) already supports multilingual models, so this is achievable without changing the STT stack. For example, SenseVoice-Small handles Korean, English, Japanese, Chinese, and Cantonese at a comparable size and is available in sherpa-onnx's model catalog.

Options, roughly in order of effort:

1. Add a transcription-language setting that selects between the current English model and a multilingual model (downloaded on demand, same flow as today).
2. Auto-select by system locale — non-English locales get the multilingual model by default.
3. Minimal: allow an advanced/config override of the model dir + type so users can supply their own sherpa-onnx model.

Happy to help test Korean transcription on a build with a multilingual model.

Environment

• Buzz Desktop on macOS (Darwin 25.5.0, Apple Silicon)
• Speaker language: Korean

[artile]

Opened #2520 for this. It makes the huddle STT model selectable (registry + BUZZ_STT_MODEL override + non-English locale auto-select) and ships Parakeet TDT 0.6B v3 as the multilingual option alongside the English default — removing the English-only hard pin that is the root cause here.

Honest caveat: Parakeet v3 covers 25 European languages only, so it does not cover Korean (the concrete case in this issue). It does, however, add the per-family config path, so a CJK model like SenseVoice-Small (KO/EN/JA/ZH/yue) is now a one-entry follow-up in the registry. Happy to add SenseVoice in the same PR if you'd prefer Korean covered directly — glad to help test it.