c

app.py

@@ -14,8 +14,8 @@ def classify_sound(file_path):
     wv, sr = torchaudio.load(file_path)
 
     # Convert to mono
-    if waveform.shape[0] > 1:
-        waveform = waveform.mean(dim=0, keepdim=True)
+    if wv.shape[0] > 1:
+        wv = wv.mean(dim=0, keepdim=True)
 
     inputs = feature_extractor(
         wv.squeeze().numpy(), sampling_rate=44100, return_tensors="pt"

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+torch
+torchaudio
+transformers