final version

app.py

@@ -3,6 +3,7 @@ import torch
 import torchaudio
 import numpy as np
 from transformers import AutoFeatureExtractor, AutoModelForAudioClassification
+import torchaudio.transforms as T
 
 MODEL_ID = "Zeyadd-Mostaffa/wav2vec_checkpoints"
 
@@ -33,13 +34,20 @@ def classify_audio(audio_file):
         waveform = torch.mean(waveform, dim=0, keepdim=True)
     waveform = waveform.squeeze()  # (samples,)
 
+    # 3) Resample if needed
+    if sr != 16000:
+        resampler = T.Resample(sr, 16000)
+        waveform = resampler(waveform)
+        sr = 16000
+
+
     # 3) Preprocess with feature_extractor
     inputs = feature_extractor(
         waveform.numpy(),
         sampling_rate=sr,
         return_tensors="pt",
         truncation=True,
-        max_length=int(feature_extractor.sampling_rate * 6.0),  # 6 second max
+        max_length=int(16000* 6.0),  # 6 second max
     )
 
     # Move everything to device