Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| from transformers import pipeline | |
| import numpy as np | |
| import json | |
| from datetime import datetime | |
| import os | |
| # Speech to text model and question-answering model | |
| s2t_model = "openai/whisper-base.en" | |
| qa_model = 'distilbert/distilbert-base-cased-distilled-squad' | |
| transcriber = pipeline('automatic-speech-recognition', model=s2t_model) | |
| qa_generator = pipeline('question-answering', model=qa_model) | |
| # List of prompts for generating the report | |
| prompts = [ | |
| {"question": "What is the business name?", "key": "business_name"}, | |
| {"question": "Who is the technician name?", "key": "technician_name"}, | |
| {"question": "Who is the customer name?", "key": "customer_name"}, | |
| {"question": "When was the inspection conducted?", "key": "inspection_date"}, | |
| {"question": "What was the vehicle inspected?", "key": "vehicle_inspected"}, | |
| {"question": "What is the VIN of the vehicle?", "key": "vehicle_vin"}, | |
| {"question": "What was the mileage of the vehicle?", "key": "vehicle_mileage"}, | |
| {"question": "What is the repair order number?", "key": "repair_order_number"}, | |
| {"question": "What was the condition of the left front tire?", "key": "left_front_tire_condition"}, | |
| {"question": "What was the condition of the right front tire?", "key": "right_front_tire_condition"}, | |
| {"question": "What was the condition of the left rear tire?", "key": "left_rear_tire_condition"}, | |
| {"question": "What was the condition of the right rear tire?", "key": "right_rear_tire_condition"}, | |
| {"question": "What was the engine oil level?", "key": "engine_oil_level"}, | |
| {"question": "What was the engine oil viscosity?", "key": "engine_oil_viscosity"}, | |
| {"question": "What was the inflation pressure of the left front tire?", "key": "left_front_inflation_pressure"}, | |
| {"question": "What was the inflation pressure of the right front tire?", "key": "right_front_inflation_pressure"}, | |
| {"question": "What was the inflation pressure of the left rear tire?", "key": "left_rear_inflation_pressure"}, | |
| {"question": "What was the inflation pressure of the right rear tire?", "key": "right_rear_inflation_pressure"}, | |
| {"question": "What was the wear pattern of the left front tire?", "key": "left_front_wear_pattern"}, | |
| {"question": "What was the wear pattern of the right front tire?", "key": "right_front_wear_pattern"}, | |
| {"question": "What was the wear pattern of the left rear tire?", "key": "left_rear_wear_pattern"}, | |
| {"question": "What was the wear pattern of the right rear tire?", "key": "right_rear_wear_pattern"}, | |
| ] | |
| def trascribe_and_answer(audio): | |
| sr, y = audio | |
| y = y.astype(np.float32) | |
| y /= np.max(np.abs(y)) | |
| context = transcriber({"sampling_rate": sr, "raw": y})["text"] | |
| # Initialize an empty dictionary to store the results | |
| results = {} | |
| # Iterate through the context and generate questions | |
| for prompt in prompts: | |
| question = prompt["question"] | |
| key = prompt["key"] | |
| # Use the question-answering model to get the answer | |
| answer = qa_generator(question=question, context=context) | |
| # Extract the answer | |
| extracted_answer = answer["answer"] | |
| # Add the result to the dictionary | |
| results[key] = extracted_answer | |
| report = { | |
| "business_name": results["business_name"], | |
| "technician_name": results["technician_name"], | |
| "customer_name": results["customer_name"], | |
| "inspection_date": results["inspection_date"], | |
| "vehicle_inspected": results["vehicle_inspected"], | |
| "vehicle_details": { | |
| "year_make_model": results["vehicle_inspected"], | |
| "VIN": results["vehicle_vin"], | |
| "mileage": results["vehicle_mileage"] | |
| }, | |
| "repair_order_number": results["repair_order_number"], | |
| "inspection_details": { | |
| "tire_condition": { | |
| "left_front": { | |
| "tread_depth": results["left_front_tire_condition"], | |
| "inflation_pressure": results["left_front_inflation_pressure"], | |
| "wear_pattern": results["left_front_wear_pattern"] | |
| }, | |
| "right_front": { | |
| "tread_depth": results["right_front_tire_condition"], | |
| "inflation_pressure": results["right_front_inflation_pressure"], | |
| "wear_pattern": results["right_front_wear_pattern"] | |
| }, | |
| "left_rear": { | |
| "tread_depth": results["left_rear_tire_condition"], | |
| "inflation_pressure": results["left_rear_inflation_pressure"], | |
| "wear_pattern": results["left_rear_wear_pattern"] | |
| }, | |
| "right_rear": { | |
| "tread_depth": results["right_rear_tire_condition"], | |
| "inflation_pressure": results["right_rear_inflation_pressure"], | |
| "wear_pattern": results["right_rear_wear_pattern"] | |
| } | |
| }, | |
| "under_hood": { | |
| "fluid_levels": { | |
| "engine_oil": { | |
| "level": results["engine_oil_level"], | |
| "viscosity": results["engine_oil_viscosity"] | |
| } | |
| } | |
| } | |
| } | |
| } | |
| current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S") | |
| # Add timestamp to the report | |
| report["timestamp"] = current_time | |
| filename = f"vehicle_inspection_report_{current_time}.json" | |
| # Save JSON report to a file | |
| with open(filename, "w") as json_file: | |
| json.dump(report, json_file, indent=4) | |
| print("Generated Vehicle Inspection Report in JSON format.") | |
| # Return JSON-like formatted output | |
| return json.dumps(report, indent=4) | |
| # Gradio interface for the audio input | |
| qa_report = gr.Interface( | |
| fn=trascribe_and_answer, | |
| inputs=gr.Audio(label="Record your inspection report:"), | |
| outputs=gr.Textbox(label="Output in JSON-like format"), | |
| title="Vehicle Inspection Report Generator", | |
| description="This tool generates a Vehicle Inspection Report based on spoken inspection results.", | |
| examples = [ | |
| [os.path.join(os.path.dirname("audio"), "Vehicle_Inspection_example.mp3")]], | |
| ) | |
| qa_report.launch() |