Spaces:
Sleeping
Sleeping
File size: 2,099 Bytes
e53f453 c8d06c3 e53f453 c8d06c3 8fa41ac 5551363 8fa41ac e53f453 c8d06c3 e53f453 c8d06c3 8fa41ac e53f453 5551363 e53f453 c8d06c3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
import os
import gradio as gr
from transformers import BarkModel, AutoProcessor
import torch
# función para el título animado
js = """
function createGradioAnimation() {
var container = document.createElement('div');
container.id = 'gradio-animation';
container.style.fontSize = '2em';
container.style.fontWeight = 'bold';
container.style.textAlign = 'center';
container.style.marginBottom = '20px';
var text = 'Audio Generation!';
for (var i = 0; i < text.length; i++) {
(function(i){
setTimeout(function(){
var letter = document.createElement('span');
letter.style.opacity = '0';
letter.style.transition = 'opacity 0.5s';
letter.innerText = text[i];
container.appendChild(letter);
setTimeout(function() {
letter.style.opacity = '1';
}, 50);
}, i * 250);
})(i);
}
var gradioContainer = document.querySelector('.gradio-container');
gradioContainer.insertBefore(container, gradioContainer.firstChild);
return 'Animation created';
}
"""
# Desactivar paralelismo en tokenizers para evitar advertencias
os.environ["TOKENIZERS_PARALLELISM"] = "false"
device = "cuda" if torch.cuda.is_available() else "cpu"
def say_something(text):
processor = AutoProcessor.from_pretrained("suno/bark-small")
model = BarkModel.from_pretrained("suno/bark-small").to(device)
inputs = processor(text)
audio_array = model.generate(**inputs)
audio_array = audio_array.cpu().numpy().squeeze()
# Devuelve el audio como un numpy array junto con el sample rate
sample_rate = model.generation_config.sample_rate
return (sample_rate, audio_array)
with gr.Blocks(js=js) as demo:
textBox = gr.Textbox(label="Text", value="Hello! [laugths]. This is a test!")
button = gr.Button("Generate Audio", variant="primary")
audio_output = gr.Audio(label="Generated Audio")
button.click(say_something, inputs=textBox, outputs=audio_output)
demo.launch()
|