Update app.py

app.py

@@ -1,7 +1,7 @@
 import torch
 import torchaudio
 from torchaudio.transforms import Resample
-from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
+from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration, SpeechEncoderDecoderModel
 import streamlit as st
 from audio_recorder_streamlit import audio_recorder
 
@@ -19,8 +19,11 @@ def preprocess_audio(audio_bytes, sample_rate=16000):
     return waveform
 
 def transcribe_audio(audio_bytes):
-    model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr")
-    processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")
+    #model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr")
+    #processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")
+    model = SpeechEncoderDecoderModel.from_pretrained("facebook/s2t-wav2vec2-large-en-de")
+    processor = Speech2Text2Processor.from_pretrained("facebook/s2t-wav2vec2-large-en-de")
+
     # Load model directly
     #processor = AutoProcessor.from_pretrained("facebook/wav2vec2-large-100k-voxpopuli")
     #model = AutoModelForPreTraining.from_pretrained("facebook/wav2vec2-large-100k-voxpopuli")