Create app.py

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import whisper
+from transformers import pipeline
+import torch
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load the Whisper model from openai-whisper
+whisper_model = whisper.load_model("tiny")
+whisper_model=whisper_model.to(device)
+
+# Load the summarization model from Hugging Face
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+
+
+
+def summarize_audio(audio_path):
+    # Step 1: Transcribe the uploaded audio file using Whisper
+    transcription_result = whisper_model.transcribe(audio_path)
+    transcription = transcription_result["text"]
+
+    # Step 2: Summarize the transcribed text using a pre-trained summarization model
+    summary = summarizer(transcription, max_length=50, min_length=25, do_sample=False)[0]['summary_text']
+
+
+    return summary
+
+# Gradio interface
+interface = gr.Interface(
+    fn=summarize_audio,  # The function to process the audio and return summarized audio
+    inputs=gr.Audio(type="filepath", label="Upload your audio file"),  # Accept audio file uploads, file path as input
+    #outputs="text",  # Provide a downloadable summarized audio file
+    outputs=gr.Textbox(label="summarized audio file"),
+    title="Audio Summarizer",  # Interface title
+    description="Upload an audio file, and this tool will summarize it.",  # Interface description
+    examples=[["audio_sample1.mp3"]]
+
+
+)
+
+# Launch the Gradio interface
+interface.launch()