Update app.py

app.py

@@ -1,64 +1,64 @@
+import whisper
+import openai
 import gradio as gr
-from huggingface_hub import InferenceClient
+from gtts import gTTS
+from moviepy.editor import VideoFileClip
+import os
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+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"]
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    # Remove temporary audio file
+    os.remove(audio_path)
+    return transcription
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+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
 
-    messages.append({"role": "user", "content": message})
+def text_to_speech(text, language="en"):
+    tts = gTTS(text=text, lang=language)
+    tts.save("summary_audio.mp3")
+    return "summary_audio.mp3"
 
-    response = ""
+def process_video(video):
+    # Transcribe the video
+    transcription = transcribe_video(video)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    # Summarize the transcription
+    summary = summarize_text(transcription)
 
-        response += token
-        yield response
+    # Convert summary to speech
+    audio_file = text_to_speech(summary)
 
+    return transcription, summary, audio_file
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+# 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()
 
-if __name__ == "__main__":
-    demo.launch()