Initial Code Commit

app.py

@@ -1,7 +1,53 @@
 import gradio as gr
+from transformers import pipeline
 
-def greet(name):
-    return "Hello " + name + "!!"
+transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base")
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+
+
+def transcribe(audio):
+    if audio is None:
+        return "", ""
+    result = transcriber(audio)
+    text = result["text"]
+    return text, ""
+
+
+def summarize(text):
+    if not text or not text.strip():
+        return "No text to summarize."
+    if len(text.split()) < 30:
+        return "Text is too short to summarize."
+    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
+    return summary[0]["summary_text"]
+
+
+with gr.Blocks(title="Audio Transcription & Summary") as demo:
+    gr.Markdown("# 🎙️ Audio Transcription & Summary")
+    gr.Markdown("Upload or record audio to transcribe it, then generate a summary.")
+
+    with gr.Row():
+        audio_input = gr.Audio(type="filepath", label="Upload or Record Audio")
+
+    with gr.Row():
+        transcribe_btn = gr.Button("Transcribe", variant="primary")
+
+    transcription_output = gr.Textbox(label="Transcription", lines=10)
+
+    with gr.Row():
+        summarize_btn = gr.Button("Summarize", variant="secondary")
+
+    summary_output = gr.Textbox(label="Summary", lines=5)
+
+    transcribe_btn.click(
+        fn=transcribe,
+        inputs=audio_input,
+        outputs=[transcription_output, summary_output],
+    )
+    summarize_btn.click(
+        fn=summarize,
+        inputs=transcription_output,
+        outputs=summary_output,
+    )
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
 demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+transformers
+torch
+gradio