app.py

import json
import whisper
import requests

medium_en = whisper.load_model("medium.en")

# def send_results_to_api(data, result_url):
#     headers = {"Content-Type": "application/json"}
#     response = requests.post(result_url, json= data, headers= headers)

#     if response.status_code == 200:
#         return response.json()
#     else:
#         return {"error": f"Failed to send results to API: {response.status_code}"}


def process_audio(params):
    try:
        params = json.loads(params)
    except json.JSONDecodeError as e:
        return {"error": f"Invalid JSON input: {e.msg} at line {e.lineno} column {e.colno}"}
    
    audio_files = params.get("urls",[])
    # api = params.get("api","")
    # job_id = params.get("job_id","")

    solutions=[]

    for audio in audio_files:
        result_medium = medium_en.transcribe(audio)
        text = result_medium['text']

        answer_dict = {}
        answer_dict.update({'url':audio, 'answer':text})
        solutions.append(answer_dict)
    # result_url = f"{api}/{job_id}"
    # send_results_to_api(solutions, result_url)

    return json.dumps({"solutions":solutions})

import gradio as gr
inputt = gr.Textbox(label="Parameters in json format   Eg. {'audio_files':['file1.mp3','file2.wav'], 'api':'https://api.example.com', 'job_id':'1001'}")
outputt = gr.JSON()

application = gr.Interface(fn=process_audio, inputs= inputt, outputs = outputt, title = "Audio Transcription with API Integration")
application.launch()