Edwardx001's picture
Upload 3 files
5c08e0a verified
|
Raw History Blame Contribute Delete
1.41 kB
metadata
title: ORCA360 Speaker Diarization
emoji: 🎙️
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: apache-2.0

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
  • 🔢 Configurable min/max number of speakers
  • 🚀 GPU-accelerated processing
  • 📡 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.