Webapp.py

# -*- coding: utf-8 -*-
"""
Created on Mon Dec  9 16:43:31 2024

@author: Pradeep Kumar
"""
import whisper
import torch
import os
from flask import Flask, request, abort, jsonify, render_template
from deep_translator import GoogleTranslator


#%%

import subprocess

# List of packages to check versions for
packages = ["whisper", "torch", "os", "flask", "deep-translator"]

# Dictionary to store versions
package_versions = {}

for package in packages:
    try:
        # Run pip show to get version info
        result = subprocess.run(
            ["pip", "show", package],
            stdout=subprocess.PIPE,
            stderr=subprocess.PIPE,
            text=True
        )
        if result.returncode == 0:
            # Parse the version from the output
            for line in result.stdout.splitlines():
                if line.startswith("Version:"):
                    package_versions[package] = line.split(":", 1)[1].strip()
        else:
            package_versions[package] = "Not Installed"
    except Exception as e:
        package_versions[package] = f"Error: {str(e)}"

package_versions


#%%

# Check if NVIDIA GPU is available
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

# Initialize Flask app
app = Flask(__name__)

# Directories for transcripts
BASE_DIR = os.getcwd()
TRANSCRIPTS_FOLDER = os.path.join(BASE_DIR, 'transcripts')

# Ensure transcripts directory exists
def check_directory(path):
    if not os.path.exists(path):
        os.makedirs(path)

check_directory(TRANSCRIPTS_FOLDER)

@app.route('/')
def upload_page():
    """
    Render the upload page for audio file submission.
    """
    return render_template('upload.html')

@app.route('/process_audio', methods=['POST'])
def process_audio():
    """
    Process audio directly from the destination using Whisper.
    """
    if 'audio_file' not in request.files:
        return abort(400, "No file part in the request.")

    audio_file = request.files['audio_file']
    selected_language = request.form.get('language', None)
    model_type = request.form.get('model_type', "base")

    if not audio_file or audio_file.filename == '':
        return abort(400, "No file selected for upload.")

    # Save the uploaded file to a temporary location
    temp_audio_path = os.path.join(BASE_DIR, audio_file.filename)
    audio_file.save(temp_audio_path)

    try:
        # Load the Whisper model based on user selection
        model = whisper.load_model(model_type, device=DEVICE)
    except Exception as e:
        return jsonify({"error": f"Failed to load Whisper model ({model_type}): {e}"}), 500

    try:
        # Transcribe with the user-selected language
        if selected_language:
            result = model.transcribe(temp_audio_path,fp16=False, language=selected_language, verbose=False)
        else:
            return abort(400, "Language selection is required.")

        # Save the transcription with timestamps
        transcript_file = os.path.join(TRANSCRIPTS_FOLDER, f"{audio_file.filename}_transcript.txt")
        
        with open(transcript_file, 'w', encoding='utf-8') as text_file:
            for segment in result['segments']:
                start_time = segment['start']
                end_time = segment['end']
                text = segment['text']
                text_file.write(f"[{start_time:.2f} - {end_time:.2f}] {text}\n")
                if selected_language == 'nl':
                    text_en = GoogleTranslator(source='auto', target='en').translate(text)
                    text_file.write(f"[{start_time:.2f} - {end_time:.2f}] {text_en}\n")

        # Return the transcription metadata
        return jsonify({
            "message": "Transcription successful!",
            "transcript_path": transcript_file,
            "transcription_preview": result['text']  
        })

    except Exception as e:
        return jsonify({"error": f"Failed to process the audio file: {e}"}), 500

    finally:
        # Clean up temporary audio file
        if os.path.exists(temp_audio_path):
            os.remove(temp_audio_path)


if __name__ == '__main__':
    # Run the Flask application
    app.run(debug=True)