Update app.py

app.py

@@ -14,8 +14,9 @@ asr_pipe = pipeline("automatic-speech-recognition", model="openai/whisper-base",
 # load text-to-speech checkpoint and speaker embeddings
 processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
 
-model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts").to(device)
-vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan").to(device)
+processor = SpeechT5Processor.from_pretrained("facebook/wav2vec2-base-960h")
+model = SpeechT5ForTextToSpeech.from_pretrained("facebook/wav2vec2-base-960h").to(device)
+vocoder = SpeechT5HifiGan.from_pretrained("facebook/wav2vec2-base-960h").to(device)
 
 embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
 speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)