Update app.py

app.py

@@ -1,17 +1,13 @@
-from transformers import pipeline
-from datasets import load_dataset
-import soundfile as sf
+from transformers import VitsModel, AutoTokenizer
 import torch
-synthetiser =pipeline('text-to-speech', model='microsoft/speecht5_tts')
-embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
-speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
-speech = synthetiser("Hello everyone!", forward_params={"speaker_embeddings": speaker_embedding})
-sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])
 
-import gradio as gr
-def text_to_speech(text):
-  speech = synthetiser(text)
-  return(speech['audio'])
+model = VitsModel.from_pretrained("facebook/mms-tts-eng")
+tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng")
 
+def generate_waveform(text):
+    inputs = tokenizer(text, return_tensors="pt")
+    with torch.no_grad():
+        output = model(**inputs).waveform
+    return (output)
 demo_text_to_speech = gr.Interface(text_to_speech, title="Text to speech converter", description="Enter a text here!", inputs='text', outputs='audio')
-demo_text_to_speech.launch()
+demo_text_to_speech.launch()