dsyoon/stt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(web): speaker diarization via pyannote (parity with whisper_stt)

Browse Source 
- Add app/diarize.py: local snapshot, A/B labels, disclaimer text
- transcribe_file and async jobs support diarize flag; Form diarize on API
- UI checkbox (default on); requirements: pyannote.audio, huggingface_hub
- README: env vars and model notes

Made-with: Cursor
This commit is contained in:
dosangyoon
2026-03-23 15:23:49 +09:00
parent 2caa74ac05
commit 26ff9b59c2
6 changed files with 280 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
requirements.txt
View File

@@ -6,3 +6,6 @@ faster-whisper
imageio-ffmpeg
psycopg[binary]
python-dotenv
# 화자 분리(웹·whisper_stt 공통): torch는 pyannote 의존성으로 설치되며, Linux에서 꼬이면 README·requirements-whisper-stt.txt 참고
huggingface_hub>=0.26.0
pyannote.audio>=3.1.0