Create app.py

app.py

@@ -0,0 +1,70 @@
+import gradio as gr
+import whisper    # Library for speech recognition
+from transformers import pipeline
+import pandas as pd
+
+
+# Load the Whisper model for speech recognition
+whisper_model = whisper.load_model("base")
+
+# Load the summarization model from Hugging Face
+summarization = pipeline("summarization", model="google/pegasus-large")
+
+def process_audio(audio_file, min_length, max_length):
+    try:
+        # Ensure audio_file is not None and has valid content
+        if audio_file is None:
+            raise ValueError("No audio file provided.")
+
+        # Use the Whisper model to transcribe the audio file into text
+        result = whisper_model.transcribe(audio_file)
+        text = result['text']
+
+        # Check if transcription was successful
+        if not text:
+            raise ValueError("Failed to transcribe the audio. The transcription result is empty.")
+
+        # Use the summarization pipeline to summarize the transcribed text
+        summary_result = summarization(text, min_length=min_length, max_length=max_length)
+        summary = summary_result[0]['summary_text']
+
+        # Check if summarization was successful
+        if not summary:
+            raise ValueError("Failed to summarize the transcript. The summary result is empty.")
+
+        # Create a DataFrame to store the audio file, transcript, and summary
+        df_results = pd.DataFrame({
+            "Audio File": [audio_file],  # Store the path to the audio file
+            "Transcript": [text],       # Store the transcribed text
+            "Summary": [summary]        # Store the generated summary
+        })
+
+        # Save the results to a CSV file named "results.csv"
+        df_results.to_csv("results.csv", index=False)
+
+        # Return the transcript and summary to be displayed in the Gradio interface
+        return text, summary
+
+    except Exception as e:
+        # General error handling
+        error_message = f"An error occurred: {str(e)}"
+        return error_message, error_message
+
+# Create a Gradio interface
+iface = gr.Interface(
+    fn=process_audio,  # The function to be called when processing the input
+    inputs=[
+        gr.Audio(sources="upload", type="filepath", label="Upload your audio file"),  # Audio input field for file upload
+        gr.Slider(minimum=10, maximum=50, value=30, label="Minimum Summary Length"),   # Slider for setting minimum summary length
+        gr.Slider(minimum=50, maximum=600, value=100, label="Maximum Summary Length")  # Slider for setting maximum summary length
+    ],
+    outputs=[
+        gr.Textbox(label="Transcript"),  # Textbox for displaying the transcript
+        gr.Textbox(label="Summary")      # Textbox for displaying the summary
+    ],
+    title="Audio to Summarized Transcript",  # Title of the app
+    description="Upload an audio file and adjust summary length to get both the transcript and summary."  # Description of the app
+)
+
+# Launch the app
+iface.launch()