Fix: Final audio processing fixes and enhanced logging

app/audio.py

@@ -77,16 +77,17 @@ def process_audio(input_data) -> torch.Tensor:
     # 4. Convert to Numpy Array (float32)
     # pydub audio is int16 or int32 generally, we want float32 [-1, 1]
     samples = np.array(audio_segment.get_array_of_samples())
+    print(f"DEBUG: Loaded samples array shape: {samples.shape}")
     
     if audio_segment.sample_width == 2:
         samples = samples.astype(np.float32) / 32768.0
     elif audio_segment.sample_width == 4:
         samples = samples.astype(np.float32) / 2147483648.0
     else:
-        # Fallback for 8-bit?
         samples = samples.astype(np.float32) / 128.0
 
     # 5. Convert to Torch Tensor [1, T]
     waveform = torch.tensor(samples).unsqueeze(0)
+    print(f"DEBUG: Output waveform tensor shape: {waveform.shape}")
     
     return waveform

inspect_b64.py

@@ -0,0 +1,17 @@
+import base64
+import io
+from pydub import AudioSegment
+import os
+
+b64_data = "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"
+
+decoded = base64.b64decode(b64_data)
+print(f"Decoded length: {len(decoded)}")
+with open("test.mp3", "wb") as f:
+    f.write(decoded)
+
+try:
+    audio = AudioSegment.from_file("test.mp3", format="mp3")
+    print("Success loading with pydub")
+except Exception as e:
+    print(f"Failed loading with pydub: {e}")