Upload folder using huggingface_hub

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 import torch
 from datasets import load_dataset
-from transformers import pipeline, SpeechT5HifiGan, SpeechT5ForTextToSpeech
+from transformers import pipeline, SpeechT5Processor, SpeechT5HifiGan, SpeechT5ForTextToSpeech
 
 model_id = "Sandiago21/speecht5_finetuned_voxpopuli_it"  # update with your model id
 # pipe = pipeline("automatic-speech-recognition", model=model_id)
@@ -10,6 +10,9 @@ vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
 embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
 speaker_embeddings = torch.tensor(embeddings_dataset[7440]["xvector"]).unsqueeze(0)
 
+checkpoint = "microsoft/speecht5_tts"
+processor = SpeechT5Processor.from_pretrained(checkpoint)
+
 def synthesize_speech(text):
     inputs = processor(text=text, return_tensors="pt")