Update app.py

app.py

@@ -3,25 +3,26 @@ import logging
 import time
 import threading
 import asyncio
-from io import BytesIO
-import requests
-import boto3
 import torch
+import boto3
 import safetensors
-import soundfile as sf
-import numpy as np
-from fastapi import FastAPI, HTTPException, Request, UploadFile, File
-from fastapi.responses import StreamingResponse
+from fastapi import FastAPI, HTTPException, Request
+from fastapi.responses import StreamingResponse, Response
 from pydantic import BaseModel, field_validator
 from transformers import (
     AutoConfig,
     AutoModelForCausalLM,
     AutoTokenizer,
     GenerationConfig,
-    StoppingCriteriaList
+    StoppingCriteriaList,
+    pipeline
 )
 from huggingface_hub import hf_hub_download
 import uvicorn
+import requests
+from io import BytesIO
+import numpy as np
+import soundfile as sf
 
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(filename)s:%(lineno)d - %(message)s")
 
@@ -70,7 +71,6 @@ class S3ModelLoader:
         return f"s3://{self.bucket_name}/lilmeaty_garca/{model_name.replace('/', '-')}"
     
     def _download_from_s3(self, model_name):
-        s3_uri = self._get_s3_uri(model_name)
         try:
             logging.info(f"Attempting to load model {model_name} from S3...")
             model_files = self.s3_client.list_objects_v2(Bucket=self.bucket_name, Prefix=f"lilmeaty_garca/{model_name}")
@@ -109,7 +109,7 @@ class S3ModelLoader:
     def download_model_from_huggingface(self, model_name):
         try:
             logging.info(f"Downloading model {model_name} from Hugging Face...")
-            model_dir = hf_hub_download(model_name, token=HUGGINGFACE_HUB_TOKEN, filename=model_name.split('/')[-1])
+            model_dir = hf_hub_download(model_name, token=HUGGINGFACE_HUB_TOKEN)
             self.s3_client.upload_file(model_dir, self.bucket_name, f"lilmeaty_garca/{model_name}")
             logging.info(f"Model {model_name} saved to S3 successfully.")
         except Exception as e: