Update app.py

app.py

@@ -2,13 +2,17 @@ import torch
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import streamlit as st
 from audio_recorder_streamlit import audio_recorder
+import numpy as np
 
 # Function to transcribe audio to text
 def transcribe_audio(audio_bytes):
     processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
     model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
 
-    input_values = processor(audio_bytes, return_tensors="pt", sampling_rate=16000).input_values
+    # Convert bytes to numpy array
+    audio_array = np.frombuffer(audio_bytes, dtype=np.int16)
+    
+    input_values = processor(audio_array, return_tensors="pt", sampling_rate=16000).input_values
     logits = model(input_values).logits
     predicted_ids = torch.argmax(logits, dim=-1)
     transcription = processor.decode(predicted_ids[0])