Update app.py

app.py

@@ -1,39 +1,38 @@
 import gradio as gr
 import whisper
 from transformers import pipeline
+from fastapi import FastAPI, UploadFile, File
+from fastapi.middleware.wsgi import WSGIMiddleware
 
-# =============== MODEL LOADING =====================
-# Load Whisper model (speech-to-text)
-whisper_model = whisper.load_model("base")  # Requires openai-whisper package
+# ================== LOAD MODELS =====================
+whisper_model = whisper.load_model("base")  # Speech-to-text
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")  # Text summarization
 
-# Load summarization model (text summarization)
-summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
-
-# =============== FUNCTION ==========================
+# ================== FUNCTION =======================
 def transcribe_and_summarize(audio_path):
     if audio_path is None:
         return "No file uploaded.", "No summary.", "API not available"
 
-    # Transcribe audio using Whisper
+    # Transcription
     try:
         result = whisper_model.transcribe(audio_path)
         transcription = result["text"]
     except Exception as e:
         return f"Transcription failed: {e}", "No summary.", "API not available"
 
-    # Summarize using Transformers
+    # Summarization
     try:
         summary = summarizer(transcription, max_length=60, min_length=10, do_sample=False)[0]["summary_text"]
     except Exception as e:
         summary = f"Summarization failed: {e}"
 
-    # Static API URL (replace with your actual space name)
-    api_link = "https://your-username-your-space-name.hf.space/api/predict/"
-    
+    # API URL (replace with your deployed Hugging Face Space or server URL)
+    api_link = "https://your-username-your-space-name.hf.space/run/predict"
+
     return transcription, summary, api_link
 
-# =============== GRADIO APP ========================
-interface = gr.Interface(
+# ================== GRADIO INTERFACE =================
+gradio_interface = gr.Interface(
     fn=transcribe_and_summarize,
     inputs=gr.Audio(type="filepath", label="Upload Audio File"),
     outputs=[
@@ -45,6 +44,28 @@ interface = gr.Interface(
     description="Upload an audio file → Transcribe it with Whisper → Summarize it using BART → Copy the API link for integration.",
 )
 
-# Entry point
+# ================== FASTAPI APP ======================
+api_app = FastAPI(title="Audio Transcriber + Summarizer API")
+
+@api_app.post("/api/transcribe/")
+async def transcribe_api(file: UploadFile = File(...)):
+    # Save uploaded file temporarily
+    temp_path = f"temp_{file.filename}"
+    with open(temp_path, "wb") as f:
+        f.write(await file.read())
+
+    # Call the same function as Gradio
+    transcription, summary, api_link = transcribe_and_summarize(temp_path)
+    
+    # Optionally, delete temp file after processing
+    os.remove(temp_path)
+    
+    return {"transcription": transcription, "summary": summary, "api_url": api_link}
+
+# ================== MOUNT GRADIO ON FASTAPI ==========
+api_app.mount("/gradio", WSGIMiddleware(gradio_interface.app))
+
+# ================== ENTRY POINT =====================
 if __name__ == "__main__":
-    interface.launch()
+    import uvicorn
+    uvicorn.run(api_app, host="0.0.0.0", port=8000)