diff --git a/src/f5_tts/infer/utils_infer.py b/src/f5_tts/infer/utils_infer.py
index 6b33bb8..1251f79 100644
--- a/src/f5_tts/infer/utils_infer.py
+++ b/src/f5_tts/infer/utils_infer.py
@@ -21,7 +21,7 @@ import numpy as np
 import torch
 import torchaudio
 import tqdm
-from huggingface_hub import snapshot_download, hf_hub_download
+from huggingface_hub import hf_hub_download
 from pydub import AudioSegment, silence
 from transformers import pipeline
 from vocos import Vocos
@@ -128,11 +128,12 @@ def load_vocoder(vocoder_name="vocos", is_local=False, local_path="", device=dev
         except ImportError:
             print("You need to follow the README to init submodule and change the BigVGAN source code.")
         if is_local:
-            """download from https://huggingface.co/nvidia/bigvgan_v2_24khz_100band_256x/tree/main"""
+            # download generator from https://huggingface.co/nvidia/bigvgan_v2_24khz_100band_256x/tree/main
             vocoder = bigvgan.BigVGAN.from_pretrained(local_path, use_cuda_kernel=False)
         else:
-            local_path = snapshot_download(repo_id="nvidia/bigvgan_v2_24khz_100band_256x", cache_dir=hf_cache_dir)
-            vocoder = bigvgan.BigVGAN.from_pretrained(local_path, use_cuda_kernel=False)
+            vocoder = bigvgan.BigVGAN.from_pretrained(
+                "nvidia/bigvgan_v2_24khz_100band_256x", use_cuda_kernel=False, cache_dir=hf_cache_dir
+            )
 
         vocoder.remove_weight_norm()
         vocoder = vocoder.eval().to(device)