# /v1/audio/diarization, /v1/audio/speaker* — pyannote + voiceprints.
#
# A SEPARATE image because pyannote.audio 3.3.2 calls
# torchaudio.AudioMetaData, which torchaudio 2.11 removed. It is not a
# conservative pin like audiocraft's was — the attribute is genuinely gone — so
# it needs an interpreter on an older torch, and that means its own venv (see
# speaker.venv-pyannote.txt) and its own image rather than 6 GB added to the
# stt image that most users pull for transcription alone.
torchaudio
transformers>=4.35.0
soundfile>=0.12.0
scipy>=1.11.0
speechbrain>=1.0.0
