import sys
import whisper
import json

audio_path = sys.argv[1]
language = sys.argv[2] if len(sys.argv) > 2 else 'ta'  # Default to Tamil if not passed

model = whisper.load_model("medium")  # or "large" for better accuracy
result = model.transcribe(audio_path, language=language)

segments = []
for seg in result['segments']:
    segments.append({
        'start': seg['start'],
        'end': seg['end'],
        'text': seg['text']
    })

print(json.dumps(segments))