Spaces:
Runtime error
Runtime error
import datasets | |
from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan | |
from datasets import load_dataset | |
import torch | |
import soundfile as sf | |
import numpy as np | |
import gradio as gr | |
import io | |
import sentencepiece | |
# Charger les modèles et les embeddings du locuteur une seule fois pour éviter de les recharger à chaque appel | |
processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts") | |
model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts") | |
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan") | |
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation") | |
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0) | |
def text_to_speech(text): | |
# Prétraiter le texte | |
inputs = processor(text=text, return_tensors="pt") | |
# Générer la parole | |
speech = model.generate_speech( | |
inputs["input_ids"], speaker_embeddings, vocoder=vocoder | |
) | |
# Enregistrer l'audio dans un buffer | |
buffer = io.BytesIO() | |
sf.write(buffer, speech.numpy(), samplerate=16000, format="WAV") | |
return buffer.getvalue() | |
# Créer l'interface Gradio | |
interface = gr.Interface( | |
fn=text_to_speech, | |
inputs="text", | |
outputs=gr.Audio(label="Processed Audio"), | |
title="Application du type Text to speech", | |
description="Entrez un texte en anglais et l'application va la traduire en audio" | |
).launch() |