diff --git a/stt-server.py b/stt-server.py index 8cba120..d806510 100755 --- a/stt-server.py +++ b/stt-server.py @@ -195,7 +195,7 @@ def transcription_worker(): break samples, duration = item try: - segments, _ = model.transcribe( + segments, info = model.transcribe( samples, language=args.language, task=args.task, @@ -213,9 +213,11 @@ def transcription_worker(): 'end': round(float(w.end), 4), 'probability': round(float(w.probability), 4), }) - log(f'transcript: {json.dumps(text.strip())} ({len(words)} words)') + language = info.language + lang_prob = round(float(info.language_probability), 3) + log(f'transcript [{language} {lang_prob}]: {json.dumps(text.strip())} ({len(words)} words)') if text.strip(): - emit({'event': 'transcript', 'text': text.strip(), 'words': words, 'duration': round(duration, 3)}) + emit({'event': 'transcript', 'text': text.strip(), 'words': words, 'duration': round(duration, 3), 'language': language, 'language_probability': lang_prob}) except Exception: msg = traceback.format_exc() log(f'transcription error:\n{msg}', error=True)