Downloads · 30 days
0
Live-Transcription
Capstone04/Live-Transcription
Live-Transcription is a automatic speech recognition model from Capstone04. Use it when you need speech turned into text.
This package provides an Automatic Speech Recognition (ASR) + Speaker Diarization pipeline using: - OpenAI Whisper - Pyannote diarization
Access
Public
Updated Nov 14, 2025
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.py15 KB · 87%
At a glance
- Task
- Automatic Speech Recognition
- Access
- Public
- Created
- Oct 29, 2025
- Updated
- Nov 14, 2025
- SHA
- 2c1a7435
Model card
From the Hugging Face model README
ASR + Diarization Pipeline
This package provides an Automatic Speech Recognition (ASR) + Speaker Diarization pipeline using:
Install
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.
- Task
- Automatic Speech Recognition
- Languages
- en
- Created
- Oct 29, 2025
- Updated
- Nov 14, 2025