Create app.py

app.py

@@ -0,0 +1,52 @@
+import gradio as gr
+import whisper
+from transformers import pipeline
+import pandas as pd
+
+# Load Whisper model for transcription
+whisper_model = whisper.load_model("base")
+
+# Load BART model for summarization
+summarization = pipeline("summarization", model="facebook/bart-large-cnn")
+
+def process_audio(audio_file, min_length, max_length):
+    try:
+        # Transcribe audio to text
+        result = whisper_model.transcribe(audio_file)
+        text = result['text']
+
+        # Summarize the transcript
+        summary_result = summarization(text, max_length=max_length, min_length=min_length)
+        summary = summary_result[0]['summary_text']
+
+        # Save results to CSV
+        df_results = pd.DataFrame({
+            "Audio File": [audio_file],
+            "Transcript": [text],
+            "Summary": [summary]
+        })
+        df_results.to_csv("results.csv", index=False)
+
+        return text, summary
+
+    except Exception as e:
+        return f"Error: {str(e)}", ""
+
+# Define Gradio interface
+iface = gr.Interface(
+    fn=process_audio,
+    inputs=[
+        gr.Audio(sources="upload", type="filepath", label="Upload your audio file"),
+        gr.Slider(minimum=5, maximum=50, value=30, label="Minimum Summary Length"),
+        gr.Slider(minimum=50, maximum=500, value=150, label="Maximum Summary Length")
+    ],
+    outputs=[
+        gr.Textbox(label="Transcript"),
+        gr.Textbox(label="Summary")
+    ],
+    title="Audio to Summarized Transcript",
+    description="Upload an audio file and adjust summary length to get both the transcript and summary."
+)
+
+# Launch the Gradio interface
+iface.launch()