Create app.py

app.py

@@ -0,0 +1,88 @@
+import os
+import csv
+import whisper
+import gradio as gr
+from transformers import pipeline
+from fastapi import FastAPI, UploadFile, File
+from fastapi.middleware.wsgi import WSGIMiddleware
+
+# ================== DIRECTORIES =====================
+UPLOAD_DIR = "uploads"
+CSV_DIR = "csv_files"
+os.makedirs(UPLOAD_DIR, exist_ok=True)
+os.makedirs(CSV_DIR, exist_ok=True)
+
+# ================== LOAD MODELS =====================
+print("Loading Whisper model...")
+whisper_model = whisper.load_model("base")
+print("Loading summarizer model...")
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+
+# ================== FUNCTION =======================
+def transcribe_and_summarize(audio_path):
+    if audio_path is None:
+        return "No file uploaded.", "No summary.", None
+
+    # Save audio to uploads folder
+    audio_filename = os.path.basename(audio_path)
+    saved_audio_path = os.path.join(UPLOAD_DIR, audio_filename)
+    if not os.path.exists(saved_audio_path):
+        os.rename(audio_path, saved_audio_path)
+
+    # Transcription
+    try:
+        result = whisper_model.transcribe(saved_audio_path)
+        transcription = result["text"]
+    except Exception as e:
+        return f"Transcription failed: {e}", "No summary.", None
+
+    # 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}"
+
+    # Save CSV
+    csv_file = os.path.join(CSV_DIR, "transcriptions.csv")
+    file_exists = os.path.isfile(csv_file)
+    with open(csv_file, mode="a", newline="", encoding="utf-8") as f:
+        writer = csv.writer(f)
+        if not file_exists:
+            writer.writerow(["Audio File", "Transcription", "Summary"])
+        writer.writerow([saved_audio_path, transcription, summary])
+
+    return transcription, summary, csv_file
+
+# ================== GRADIO INTERFACE =================
+gradio_interface = gr.Interface(
+    fn=transcribe_and_summarize,
+    inputs=gr.Audio(type="filepath", label="Upload Audio File"),
+    outputs=[
+        gr.Textbox(label="🔊 Transcription"),
+        gr.Textbox(label="📝 Summary"),
+        gr.File(label="📄 Download CSV with Audio Links")
+    ],
+    title="🎤 Audio Transcriber + Summarizer",
+    description="Upload an audio file → Transcribe it with Whisper → Summarize it using BART → Download CSV."
+)
+
+# ================== 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"/tmp/{file.filename}"
+    with open(temp_path, "wb") as f:
+        f.write(await file.read())
+
+    transcription, summary, csv_file = transcribe_and_summarize(temp_path)
+    return {"transcription": transcription, "summary": summary, "csv_file": csv_file}
+
+# Mount Gradio on FastAPI
+api_app.mount("/gradio", WSGIMiddleware(gradio_interface.launch(prevent_thread_lock=True)))
+
+# ================== ENTRY POINT =====================
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(api_app, host="0.0.0.0", port=8000)