diff --git a/dikte/api.py b/dikte/api.py index c83be1b..0d07883 100644 --- a/dikte/api.py +++ b/dikte/api.py @@ -465,7 +465,7 @@ def transcribe_detected(target, audio_path, language="", prompt="", timeout=300, The spoken language is only knowable when the transcription model reports it, and only whisper.cpp does: the hosted endpoints accept "auto" but never say what they heard. So detection is asked for exactly where it can be - answered — the local server, in auto mode — and every other run transcribes + answered, the local server in auto mode, and every other run transcribes as before and hands back an empty code. """ if target.provider == "local" and language == "auto": diff --git a/dikte/config.py b/dikte/config.py index b46f7b2..aaaacd7 100644 --- a/dikte/config.py +++ b/dikte/config.py @@ -709,8 +709,8 @@ class Config: """`speech` is the two-letter code of the language that was heard, when the transcription model reported one. The default prompts and the glossary rule only exist in Turkish and English, so a detected Turkish - recording gets the Turkish prompt and any other detected language — or - none at all — the English one, which is written not to care what + recording gets the Turkish prompt and any other detected language, or + none at all, the English one, which is written not to care what language the transcript is in. Nothing else calls this with it, so the interface language keeps deciding everywhere the speech was not asked about."""