pipelines/ai_inference.py

import openai
import whisper
import json

def transcribe_audio(audio_file):
    # Option A: local Whisper
    model = whisper.load_model("base")
    result = model.transcribe(audio_file)
    return result["text"]

def generate_edit_instructions(transcript_text):
    system_msg = """You are a video editing assistant..."""
    user_msg = f"Transcript:\n{transcript_text}\n\nOutput instructions in JSON..."

    # GPT-based approach
    response = openai.ChatCompletion.create(
        model="gpt-4",
        messages=[
            {"role": "system", "content": system_msg},
            {"role": "user", "content": user_msg}
        ],
    )
    return response.choices[0].message["content"]