---
language: en
tags:
- asr
- diarization
pipeline_tag: automatic-speech-recognition
---
# ASR + Diarization Pipeline

This package provides an **Automatic Speech Recognition (ASR) + Speaker Diarization** pipeline using:
- [OpenAI Whisper](https://huggingface.co/openai/whisper-medium)
- [Pyannote diarization](https://huggingface.co/pyannote/speaker-diarization-3.1)

## Install
```bash
pip install git+https://huggingface.co/Capstone04/live-transcription-pipeline

## Speaker Identification
You can now enroll known speakers by providing reference audio samples. The pipeline will match incoming speaker segments against stored embeddings and label them accordingly. Unknown speakers are dynamically tracked per session.