Add transcription and topic extraction app

README.md

@@ -1,12 +1,11 @@
----
-title: MyIVR
-emoji: 🏃
-colorFrom: blue
-colorTo: pink
-sdk: gradio
-sdk_version: 5.12.0
-app_file: app.py
-pinned: false
----
+# Audio Transcription and Topic Extraction
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+This app allows you to upload an audio file, transcribe it to text, and extract the main topics using machine learning models.
+
+## Features
+- Transcription powered by OpenAI's Whisper.
+- Topic extraction using Hugging Face Transformers.
+
+## Usage
+- Upload an audio file.
+- View the transcription and extracted topics.

app.py

@@ -1,7 +1,33 @@
+import whisper
 import gradio as gr
+from transformers import pipeline
 
-def greet(name):
-    return "Hello " + name + "!!"
+# Load models
+def transcribe_audio(file_path):
+    model = whisper.load_model("base")  # Use "tiny", "base", "small", etc.
+    result = model.transcribe(file_path)
+    return result["text"]
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+def extract_topics(text):
+    summarizer = pipeline("summarization")
+    summary = summarizer(text, max_length=50, min_length=25, do_sample=False)
+    return summary[0]["summary_text"]
+
+def process_audio(file):
+    # Transcribe the audio file
+    transcript = transcribe_audio(file.name)
+    # Extract topics from the transcription
+    topics = extract_topics(transcript)
+    return transcript, topics
+
+# Gradio interface
+interface = gr.Interface(
+    fn=process_audio,
+    inputs=gr.Audio(source="upload", type="filepath"),
+    outputs=["text", "text"],
+    title="Audio Transcription and Topic Extraction",
+    description="Upload an audio file to get a transcription and extract main topics."
+)
+
+if __name__ == "__main__":
+    interface.launch()

requirements.txt

@@ -0,0 +1,4 @@
+openai-whisper
+gradio
+transformers
+torch  # Required by Whisper