- add WhisperX diarization support to the Whisper VM server - normalize speaker timestamp segments from Whisper responses - document Hugging Face/pyannote VM setup and health checks - show diarized speaker transcript blocks in record and transcript views - group consecutive segments from the same speaker - remove duplicate paragraph transcript display when diarized segments exist - let diarized transcript content expand without an inner scrollbar
2.3 KiB
Faster-Whisper VM Setup
The sample env expects the Whisper service to run on the VM at 172.16.10.64:8000.
The backend expects a Whisper-compatible HTTP service:
WHISPER_VM_IP=172.16.10.64
WHISPER_VM_PORT=8000
WHISPER_API_URL=http://172.16.10.64:8000
WHISPER_TRANSCRIBE_PATH=/transcribe
WHISPER_HEALTH_PATH=/health
WHISPER_FILE_FIELD=file
WHISPER_ALLOW_MOCK=false
Expected endpoints:
GET /healthreturns any 2xx status when the VM is ready. For WhisperX diarization, it should also report"whisperx": trueand"diarization": true.POST /transcribeaccepts multipart audio and returns one of:
{
"transcript_text": "Meeting transcript...",
"language": "en",
"duration": 123.45,
"timestamps": [{ "speaker": "Speaker 1", "start": 0, "end": 5, "text": "Hello" }]
}
The API retries failed requests, applies WHISPER_TIMEOUT_MS, and marks jobs as failed when the VM
is unavailable.
Enable WhisperX diarization on the VM
The systemd unit runs /home/cezen/whisper/server.py inside the existing
/home/cezen/whisper/venv. Deploy the updated script without creating a new venv:
scp scripts/whisper_http_server.py cezen@172.16.10.64:/home/cezen/whisper/server.py
scp scripts/orphion-whisper.service cezen@172.16.10.64:/tmp/orphion-whisper.service
ssh cezen@172.16.10.64 'sudo mv /tmp/orphion-whisper.service /etc/systemd/system/orphion-whisper.service'
Create /home/cezen/whisper/.env on the VM with the HuggingFace token accepted by pyannote:
HUGGINGFACE_TOKEN=your_token_here
WHISPERX_DIARIZATION=true
WHISPERX_DEVICE=cuda
WHISPERX_COMPUTE_TYPE=float16
WHISPERX_BATCH_SIZE=8
WHISPERX_DIARIZATION_MODEL=pyannote/speaker-diarization-community-1
The HuggingFace account behind the token must be approved for the configured pyannote diarization
model. If transcription returns "diarization": "fallback" and the service log mentions a gated
repo, visit https://huggingface.co/pyannote/speaker-diarization-community-1 while signed in to
that account and accept/request access.
Restart and verify:
ssh cezen@172.16.10.64 'sudo systemctl daemon-reload && sudo systemctl restart orphion-whisper'
curl -sS http://172.16.10.64:8000/health
Expected health shape:
{ "status": "ok", "model": "large-v3", "device": "cuda", "whisperx": true, "diarization": true }