Update app.py

app.py

@@ -4,8 +4,11 @@ import numpy as np
 from generator import load_csm_1b
 import torchaudio
 
-# Load CSM model
-generator = load_csm_1b(device="cpu") 
+# Load the configuration manually
+config = AutoConfig.from_pretrained("sesame/csm-1b")
+
+# Load the model with config
+generator = load_csm_1b(device="cpu", config=config)
 
 # Load image-to-text model
 captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")