Update app.py

app.py

@@ -8,7 +8,20 @@ tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
 
 #load audio file
-speech, rate = librosa.load("batman1.wav",sr=16000)
+speech, rate = librosa.load("/hip-voice.m4a",sr=16000)
+
+import IPython.display as display
+display.Audio("batman1.wav", autoplay=True)
+
+input_values = tokenizer(speech, return_tensors = 'pt').input_values
+logits = model(input_values).logits
+
+predicted_ids = torch.argmax(logits, dim =-1)
+
+#decode the audio to generate text
+transcriptions = tokenizer.decode(predicted_ids[0])
+
+print(transcriptions)