Update app.py

app.py

@@ -12,16 +12,11 @@ model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
 
 def transcribe(file_):
     arr_audio, _ = librosa.load(file_, sr=16000)
-    inputs = processor(arr_audio, sampling_rate=16_000, return_tensors="pt", padding=True)
-
-    with torch.no_grad():
-        logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
-
-    pred_ids = torch.argmax(logits, dim=-1)
-    text = processor.batch_decode(pred_ids)[0]
-    return text.lower()
-
-
+    input_values = processor(arr_audio, return_tensors="pt", padding="longest").input_values
+    logits = model(input_values).logits
+    predicted_ids = torch.argmax(logits, dim=-1)
+    transcription = processor.batch_decode(predicted_ids)
+    return transcription[0].lower()
 
 
 iface = gr.Interface(