ORCA360 Speaker Diarization API

This Space provides speaker diarization capabilities for the ORCA360 automated assessment platform.

Features

  • 🎀 Speaker identification in audio recordings
  • ⏱️ Timestamp-based speaker segmentation
  • πŸ”’ Configurable min/max number of speakers
  • πŸš€ GPU-accelerated processing
  • πŸ“‘ API access available

Usage

Web Interface

  1. Upload an audio file (WAV, MP3, M4A)
  2. Optionally specify min/max speakers
  3. Click "Diarize"
  4. View results with speaker segments and timestamps

API Access

from gradio_client import Client

client = Client("Edwardx001/ragasa-diarization")
result = client.predict(
    audio_file="path/to/audio.wav",
    min_speakers=None,
    max_speakers=None,
    api_name="/predict"
)
print(result)

cURL Example

curl -X POST https://edwardx001-ragasa-diarization.hf.space/api/predict \
  -F "data=@audio.wav"

Model

Uses pyannote/speaker-diarization-3.1

License

Apache 2.0

Project

Part of the ORCA360 aviation training assessment platform.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support