War of Words
Multilingual Video Transcription System
A multilingual transcription and search system that turns raw video into diarized, translated, searchable transcripts.
What we built
- AzureML transcription pipeline using WhisperX with PyAnnote diarization
- MongoDB vector database for similarity search over audio embeddings
- Automated English translation through the ChatGPT API
Delivered by Pavlo Holubchykov, Raw Code's Lead ML/AI Developer.
Outcome metrics for this project haven't been independently verified yet — figures will be added here once confirmed rather than estimated.
More work
Want something like this built?
Book a call