efforting.tech/stt-server
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Include detected language and confidence in transcript events

Browse Source 
Unpacks transcription info instead of discarding it. Adds language and
language_probability fields to transcript events, and includes them in
verbose log output.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
mikael-lovqvists-claude-agent
2026-06-07 09:21:44 +00:00
parent bdb1aac885
commit 0afe761625
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
stt-server.py
View File

@@ -195,7 +195,7 @@ def transcription_worker():
break break
samples, duration = item samples, duration = item
try: try:
segments, _ = model.transcribe( segments, info = model.transcribe(
samples, samples,
language=args.language, language=args.language,
task=args.task, task=args.task,
@@ -213,9 +213,11 @@ def transcription_worker():
'end': round(float(w.end), 4), 'end': round(float(w.end), 4),
'probability': round(float(w.probability), 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(): 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: except Exception:
msg = traceback.format_exc() msg = traceback.format_exc()
log(f'transcription error:\n{msg}', error=True) log(f'transcription error:\n{msg}', error=True)