Spaces:
Running
Running
File size: 5,208 Bytes
c2a2b08 47703c3 c2a2b08 47703c3 c2a2b08 9657edf c2a2b08 9657edf c2a2b08 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 |
import argparse
from concurrent.futures import ProcessPoolExecutor
import logging
import os
from pathlib import Path
import subprocess as sp
import sys
from tempfile import NamedTemporaryFile
import time
import typing as tp
import warnings
import torch
import gradio as gr
from audiocraft.data.audio_utils import convert_audio
from audiocraft.data.audio import audio_write
from audiocraft.models import MusicGen
MODEL = None # Last used model
INTERRUPTING = False
pool = ProcessPoolExecutor(4)
pool.__enter__()
class FileCleaner:
def __init__(self, file_lifetime: float = 3600):
self.file_lifetime = file_lifetime
self.files = []
def add(self, path: tp.Union[str, Path]):
self._cleanup()
self.files.append((time.time(), Path(path)))
def _cleanup(self):
now = time.time()
for time_added, path in list(self.files):
if now - time_added > self.file_lifetime:
if path.exists():
path.unlink()
self.files.pop(0)
else:
break
file_cleaner = FileCleaner()
def load_model(version='facebook/musicgen-small'):
global MODEL
print("Loading model", version)
if MODEL is None or MODEL.name != version:
del MODEL
torch.cuda.empty_cache()
MODEL = None
MODEL = MusicGen.get_pretrained(version)
def _do_predictions(texts, duration):
MODEL.set_generation_params(duration=duration)
outputs = MODEL.generate(texts)
outputs = outputs.detach().cpu().float()
out_wavs = []
for output in outputs:
with NamedTemporaryFile("wb", suffix=".wav", delete=False) as file:
audio_write(
file.name, output, MODEL.sample_rate, strategy="loudness",
loudness_headroom_db=16, loudness_compressor=True, add_suffix=False)
out_wavs.append(file.name)
file_cleaner.add(file.name)
return out_wavs
def predict(text, duration):
load_model('facebook/musicgen-small')
wav_files = _do_predictions([text], duration)
return wav_files[0] # Return the first file in the list
def ui(launch_kwargs):
with gr.Blocks() as demo:
gr.Markdown(
"""
# MelodyLM: Generate Music from Text.
Team Members:
1. Sunil Gopal C V
2. Sudhan S
3. Shreyas Gutti Srinivas
4. Sushanth R
"""
)
with gr.Row():
text = gr.Text(label="Input Text", interactive=True)
duration = gr.Slider(minimum=1, maximum=120, value=10, label="Duration", interactive=True)
submit = gr.Button("Submit")
with gr.Row():
audio_output = gr.Audio(label="Generated Music", type='filepath')
submit.click(predict, inputs=[text, duration], outputs=[audio_output])
gr.Markdown("""
## Guide:
### Input:
1. Text Structure: Provide a short, descriptive phrase or sentence that encapsulates the mood, genre, and style of the music you want. For example, "Pop dance track with catchy melodies, tropical percussion, and upbeat rhythms, perfect for the beach."
2. Keywords and Phrases: Mention specific musical elements you want to include, such as instruments (e.g., guitar, piano), styles (e.g., jazz, classical), or other characteristics (e.g., slow, fast, mellow, energetic).
3. Examples:
- Example 1: "Relaxing ambient track with soft piano, gentle synths, and a serene atmosphere."
- Example 2: "Energetic rock song with electric guitar riffs, powerful drums, and a lively tempo."
### Output:
You can play, pause, and download the generated music track based on your input description.
""")
demo.queue(max_size=8 * 4).launch(**launch_kwargs)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
'--listen',
type=str,
default='0.0.0.0' if 'SPACE_ID' in os.environ else '127.0.0.1',
help='IP to listen on for connections to Gradio',
)
parser.add_argument(
'--username', type=str, default='', help='Username for authentication'
)
parser.add_argument(
'--password', type=str, default='', help='Password for authentication'
)
parser.add_argument(
'--server_port',
type=int,
default=0,
help='Port to run the server listener on',
)
parser.add_argument(
'--inbrowser', action='store_true', help='Open in browser'
)
parser.add_argument(
'--share', action='store_true', help='Share the gradio UI'
)
args = parser.parse_args()
launch_kwargs = {}
launch_kwargs['server_name'] = args.listen
if args.username and args.password:
launch_kwargs['auth'] = (args.username, args.password)
if args.server_port:
launch_kwargs['server_port'] = args.server_port
if args.inbrowser:
launch_kwargs['inbrowser'] = args.inbrowser
if args.share:
launch_kwargs['share'] = args.share
logging.basicConfig(level=logging.INFO, stream=sys.stderr)
# Show the interface
ui(launch_kwargs)
|