Create app.py

app.py

@@ -0,0 +1,65 @@
+import whisper
+import openai
+import gradio as gr
+from gtts import gTTS
+from moviepy.editor import VideoFileClip
+import os
+
+openai.api_key = "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"
+
+def transcribe_video(video_path):
+    # Extract audio from video file
+    video = VideoFileClip(video_path)
+    audio_path = "temp_audio.wav"
+    video.audio.write_audiofile(audio_path, codec='pcm_s16le')
+
+    # Load Whisper model and transcribe audio
+    model = whisper.load_model("base")
+    result = model.transcribe(audio_path)
+    transcription = result["text"]
+    
+    # Remove temporary audio file
+    os.remove(audio_path)
+    return transcription
+
+def summarize_text(text):
+    response = openai.Completion.create(
+        engine="text-davinci-003",
+        prompt=f"Summarize the following text:\n\n{text}",
+        max_tokens=150
+    )
+    summary = response.choices[0].text.strip()
+    return summary
+
+def text_to_speech(text, language="en"):
+    tts = gTTS(text=text, lang=language)
+    tts.save("summary_audio.mp3")
+    return "summary_audio.mp3"
+
+def process_video(video):
+    # Transcribe the video
+    transcription = transcribe_video(video)
+    
+    # Summarize the transcription
+    summary = summarize_text(transcription)
+    
+    # Convert summary to speech
+    audio_file = text_to_speech(summary)
+    
+    return transcription, summary, audio_file
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=process_video,
+    inputs=gr.Video(label="Upload Video"),
+    outputs=[
+        gr.Textbox(label="Transcription"),
+        gr.Textbox(label="Summary"),
+        gr.Audio(label="Summary Audio")
+    ],
+    title="Video Transcription and Summarization",
+    description="Upload a video file to transcribe and summarize its content."
+)
+
+# Launch the interface
+iface.launch()