Update app.py

app.py

@@ -9,6 +9,11 @@ from transformers import AutoProcessor, ClapModel
 from model.udit import UDiT
 from vae_modules.autoencoder_wrapper import Autoencoder
 import numpy as np
+from huggingface_hub import snapshot_download
+
+snapshot_download(repo_id="laion/larger_clap_general", 
+                  local_dir="./larger_clap_general", 
+                  local_dir_use_symlinks=False)
 
 diffusion_config = './config/SoloAudio.yaml'
 diffusion_ckpt = './pretrained_models/soloaudio_v2.pt'
@@ -22,8 +27,8 @@ with open(diffusion_config, 'r') as fp:
 
 v_prediction = diff_config["ddim"]["v_prediction"]
 
-clapmodel = ClapModel.from_pretrained("laion/larger_clap_general").to(device)
-processor = AutoProcessor.from_pretrained('laion/larger_clap_general')
+clapmodel = ClapModel.from_pretrained("./larger_clap_general").to(device)
+processor = AutoProcessor.from_pretrained('./larger_clap_general')
 autoencoder = Autoencoder(autoencoder_path, 'stable_vae', quantization_first=True)
 autoencoder.eval()
 autoencoder.to(device)