File size: 1,249 Bytes
f475ceb |
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 |
import torch
import torchaudio
from einops import rearrange
import gradio as gr
from stable_audio_tools import get_pretrained_model
from stable_audio_tools.inference.generation import generate_diffusion_cond
device = "cuda" if torch.cuda.is_available() else "cpu"
model, config = get_pretrained_model("stabilityai/stable-audio-open-small")
model = model.to(device)
sample_rate = config["sample_rate"]
sample_size = config["sample_size"]
def generate_audio(prompt):
conditioning = [{"prompt": prompt, "seconds_total": 11}]
with torch.no_grad():
output = generate_diffusion_cond(
model,
steps=8,
conditioning=conditioning,
sample_size=sample_size,
device=device
)
output = rearrange(output, "b d n -> d (b n)")
output = output.to(torch.float32).div(torch.max(torch.abs(output))).clamp(-1, 1).mul(32767).to(torch.int16).cpu()
path = "output.wav"
torchaudio.save(path, output, sample_rate)
return path
ui = gr.Interface(fn=generate_audio,
inputs=gr.Textbox(label="Prompt (e.g. 128 BPM tech house drum loop)"),
outputs=gr.Audio(type="filepath"),
title="Stable Audio Generator")
ui.launch()
|