bellingcat / whisperbox-transcribe

Easy to deploy API for transcribing and translating audio / video using OpenAI's whisper model.

bellingcat/whisperbox-transcribe Issues

Dependency Dashboard
Updated 4 months ago
worker dies from not being able to connect to rabbitmq
Updated 4 months ago2
Add additional task metadata and logs
Updated 9 months ago
Add new endpoint that triggers both translate and transcribe tasks
Updated 9 months ago
fastapi.exceptions.ResponseValidationError with make dev
Closed 10 months ago
Add deployment instructions
Closed 10 months ago
Add remote transcription strategy
Updated a year ago
Fix disk space leaking when transcription job fails
Closed a year ago
Add API route to retrieve config
Closed a year ago
Add reverse proxy to production docker compose
Closed a year ago
Use `.en` model for jobs with `config.language=en`
Closed a year ago
Allow changing model via API
Closed a year ago
Add docker production deployments
Closed a year ago
Improve OpenAPI documentation
Closed a year ago