File size: 5,841 Bytes
5238467 1897b6f 5238467 9138f15 5238467 1897b6f 5238467 9138f15 5238467 1897b6f 5238467 1897b6f 9d7284e 1897b6f 5238467 9d7284e 5238467 1897b6f 5238467 cacee96 5238467 9d7284e 13fbecc 9d7284e 5238467 1897b6f 7aceb80 1897b6f 7aceb80 1897b6f 5238467 |
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 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 |
"""
Copyright (c) Meta Platforms, Inc. and affiliates.
All rights reserved.
This source code is licensed under the license found in the
LICENSE file in the root directory of this source tree.
"""
from tempfile import NamedTemporaryFile
import torch
import gradio as gr
from audiocraft.models import MusicGen
from audiocraft.data.audio import audio_write
MODEL = None
def load_model(version):
print("Loading model", version)
return MusicGen.get_pretrained(version)
def predict(model, text, melody, duration, topk, topp, temperature, cfg_coef):
global MODEL
topk = int(topk)
if MODEL is None or MODEL.name != model:
MODEL = load_model(model)
if duration > MODEL.lm.cfg.dataset.segment_duration:
raise gr.Error("MusicGen currently supports durations of up to 30 seconds!")
MODEL.set_generation_params(
use_sampling=True,
top_k=topk,
top_p=topp,
temperature=temperature,
cfg_coef=cfg_coef,
duration=duration,
)
if melody:
sr, melody = melody[0], torch.from_numpy(melody[1]).to(MODEL.device).float().t().unsqueeze(0)
print(melody.shape)
if melody.dim() == 2:
melody = melody[None]
melody = melody[..., :int(sr * MODEL.lm.cfg.dataset.segment_duration)]
output = MODEL.generate_with_chroma(
descriptions=[text],
melody_wavs=melody,
melody_sample_rate=sr,
progress=False
)
else:
output = MODEL.generate(descriptions=[text], progress=False)
output = output.detach().cpu().float()[0]
with NamedTemporaryFile("wb", suffix=".wav", delete=False) as file:
audio_write(file.name, output, MODEL.sample_rate, strategy="loudness", add_suffix=False)
waveform_video = gr.make_waveform(file.name)
return waveform_video
with gr.Blocks() as demo:
gr.Markdown(
"""
# MusicGen
This is the demo for [MusicGen](https://github.com/facebookresearch/audiocraft), a simple and controllable model for music generation
presented at: ["Simple and Controllable Music Generation"](https://huggingface.co/papers/2306.05284).
<br/>
<a href="https://huggingface.co/spaces/musicgen/MusicGen?duplicate=true" style="display: inline-block;margin-top: .5em;margin-right: .25em;" target="_blank">
<img style="margin-bottom: 0em;display: inline;margin-top: -.25em;" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
for longer sequences, more control and no queue.</p>
"""
)
with gr.Row():
with gr.Column():
with gr.Row():
text = gr.Text(label="Input Text", interactive=True)
melody = gr.Audio(source="upload", type="numpy", label="Melody Condition (optional)", interactive=True)
with gr.Row():
submit = gr.Button("Submit")
with gr.Row():
model = gr.Radio(["melody", "medium", "small", "large"], label="Model", value="melody", interactive=True)
with gr.Row():
duration = gr.Slider(minimum=1, maximum=30, value=10, label="Duration", interactive=True)
with gr.Row():
topk = gr.Number(label="Top-k", value=250, interactive=True)
topp = gr.Number(label="Top-p", value=0, interactive=True)
temperature = gr.Number(label="Temperature", value=1.0, interactive=True)
cfg_coef = gr.Number(label="Classifier Free Guidance", value=3.0, interactive=True)
with gr.Column():
output = gr.Video(label="Generated Music")
submit.click(predict, inputs=[model, text, melody, duration, topk, topp, temperature, cfg_coef], outputs=[output])
gr.Examples(
fn=predict,
examples=[
[
"An 80s driving pop song with heavy drums and synth pads in the background",
"./assets/bach.mp3",
"melody"
],
[
"A cheerful country song with acoustic guitars",
"./assets/bolero_ravel.mp3",
"melody"
],
[
"90s rock song with electric guitar and heavy drums",
None,
"medium"
],
[
"a light and cheerly EDM track, with syncopated drums, aery pads, and strong emotions",
"./assets/bach.mp3",
"melody"
],
[
"lofi slow bpm electro chill with organic samples",
None,
"medium",
],
],
inputs=[text, melody, model],
outputs=[output]
)
gr.Markdown(
"""
### More details
The model will generate a short music extract based on the description you provided.
You can generate up to 30 seconds of audio.
We present 4 model variations:
1. Melody -- a music generation model capable of generating music condition on text and melody inputs. **Note**, you can also use text only.
2. Small -- a 300M transformer decoder conditioned on text only.
3. Medium -- a 1.5B transformer decoder conditioned on text only.
4. Large -- a 3.3B transformer decoder conditioned on text only (might OOM for the longest sequences.)
When using `melody`, ou can optionaly provide a reference audio from
which a broad melody will be extracted. The model will then try to follow both the description and melody provided.
You can also use your own GPU or a Google Colab by following the instructions on our repo.
See [github.com/facebookresearch/audiocraft](https://github.com/facebookresearch/audiocraft)
for more details.
"""
)
demo.launch()
|