Check if the API is running:
curl -X GET http://localhost:5016/Send an audio file for transcription:
curl -X POST http://localhost:5016/api/inference/ \
-F "audio_file=@/path/to/your/audio/file.mp3" \
-F "num_speakers=2"audio_file: The audio file to transcribe (required)num_speakers: The number of speakers to identify in the audio (optional)
Check if the models are loaded correctly:
curl -X GET http://localhost:5016/debug/modelsThe API will return a JSON response with the transcribed segments:
{
"segments": [
{
"speaker": "SPEAKER_0",
"start": 0.5,
"end": 5.2,
"transcription": "Transcribed text for speaker 0"
},
{
"speaker": "SPEAKER_1",
"start": 5.8,
"end": 10.3,
"transcription": "Transcribed text for speaker 1"
}
]
}