app.py

from flask import Flask, request, render_template, redirect, url_for
import os
from moviepy.editor import VideoFileClip
import whisper

app = Flask(__name__)
from flask import Flask, request, render_template, redirect, url_for
import os
from moviepy.editor import VideoFileClip
import whisper

app = Flask(__name__)

# Set ffmpeg path for the Docker container environment
ffmpeg_path = r'/usr/bin/ffmpeg'
if not os.path.isdir(ffmpeg_path):
    raise FileNotFoundError(f"FFmpeg directory not found: {ffmpeg_path}")
os.environ['PATH'] += os.pathsep + ffmpeg_path

# Load the Whisper model
model = whisper.load_model("medium")  # Change to "large" for the most accurate model

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/upload', methods=['POST'])
def upload_video():
    if 'video' not in request.files:
        return redirect(url_for('index'))

    video_file = request.files['video']
    if video_file.filename == '':
        return redirect(url_for('index'))

    # Save the video file
    video_path = os.path.join('uploads', video_file.filename)
    video_file.save(video_path)

    print(f"Video saved to {video_path}")

    # Extract audio from the video
    try:
        audio_path = extract_audio(video_path)
        print(f"Audio extracted to {audio_path}")
        if not os.path.exists(audio_path):
            return f"Error: Audio file not found at {audio_path}"
    except Exception as e:
        return f"Error extracting audio: {e}"

    # Transcribe the audio
    try:
        transcript = transcribe_audio(audio_path)
    except Exception as e:
        return f"Error transcribing audio: {e}"

    return render_template('result.html', transcript=transcript)

def extract_audio(video_path):
    audio_path = os.path.splitext(video_path)[0] + ".wav"
    video = VideoFileClip(video_path)
    video.audio.write_audiofile(audio_path)
    return audio_path

def transcribe_audio(audio_path):
    print(f"Transcribing audio from: {audio_path}")
    if not os.path.exists(audio_path):
        raise FileNotFoundError(f"Audio file not found at {audio_path}")

    try:
        os.system("ffmpeg -version")
        print("FFmpeg is available")
    except Exception as e:
        print(f"FFmpeg is not available: {e}")
        raise

    try:
        result = model.transcribe(audio_path)
        print(f"Transcription result: {result}")
        return result["text"]
    except Exception as e:
        print(f"Error during transcription: {e}")
        raise

if __name__ == '__main__':
    if not os.path.exists('uploads'):
        os.makedirs('uploads')
    app.run(debug=True)

# Add ffmpeg to the PATH
ffmpeg_path = r'/usr/bin/ffmpeg'  # Path for ffmpeg in the Docker container

# Load the Whisper model
model = whisper.load_model("medium")  # Change to "large" for the most accurate model

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/upload', methods=['POST'])
def upload_video():
    if 'video' not in request.files:
        return redirect(url_for('index'))

    video_file = request.files['video']
    if video_file.filename == '':
        return redirect(url_for('index'))

    # Save the video file
    video_path = os.path.join('uploads', video_file.filename)
    video_file.save(video_path)

    try:
        # Extract audio from the video
        audio_path = extract_audio(video_path)
        # Transcribe the audio
        transcript = transcribe_audio(audio_path)
    except Exception as e:
        return f"Error: {e}"

    return render_template('result.html', transcript=transcript, model_name="medium")  # Adjust model name accordingly

def extract_audio(video_path):
    audio_path = os.path.splitext(video_path)[0] + ".wav"
    try:
        video = VideoFileClip(video_path)
        video.audio.write_audiofile(audio_path)
    except Exception as e:
        raise RuntimeError(f"Error extracting audio: {e}")
    return audio_path

def transcribe_audio(audio_path):
    if not os.path.exists(audio_path):
        raise FileNotFoundError(f"Audio file not found at {audio_path}")

    try:
        result = model.transcribe(audio_path)
        return result["text"]
    except Exception as e:
        raise RuntimeError(f"Error during transcription: {e}")