feat: create inference ws server

inference_server.py

@@ -0,0 +1,30 @@
+import asyncio
+from websockets.server import serve
+
+# from generate import generate
+
+
+async def handler(websocket):
+    async for message in websocket:
+        if message != "generate":
+            continue
+
+        print("generating new audio clips...")
+
+        # generate()
+
+        print("audio generated")
+
+        for i in range(5):
+            with open(f"{i + 5}.mp3", "rb") as f:
+                data = f.read()
+                await websocket.send(data)
+
+
+async def main():
+    async with serve(handler, "", 8001):
+        await asyncio.Future()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())