qwe

main.py

@@ -109,7 +109,11 @@ def extract_audio_features(file_path: str) -> np.ndarray:
     embeddings = []
     for chunk in chunks:
         try:
-            inputs = clap_processor(audio=chunk, sampling_rate=48000, return_tensors="pt")
+            inputs = clap_processor(
+    audios=chunk,
+    sampling_rate=48000,
+    return_tensors="pt"
+)
             with torch.no_grad():
                 emb = clap_model(**inputs).audio_embeds.squeeze().numpy()
             embeddings.append(emb)