File size: 1,944 Bytes
72c877e
 
 
 
c17b696
72c877e
d533c9c
 
 
 
 
 
 
 
 
 
72c877e
02a7301
 
 
 
2b5d8ed
 
02a7301
 
 
 
600e950
2b5d8ed
 
02a7301
 
 
 
 
 
 
 
 
 
72c877e
 
 
 
 
 
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
import argparse

import gradio as gr

from audiodiffusion import AudioDiffusion


def generate_spectrogram_audio_and_loop(model_id):
    audio_diffusion = AudioDiffusion(model_id=model_id)
    image, (sample_rate,
            audio) = audio_diffusion.generate_spectrogram_and_audio()
    loop = AudioDiffusion.loop_it(audio, sample_rate)
    if loop is None:
        loop = audio
    return image, (sample_rate, audio), (sample_rate, loop)


demo = gr.Interface(fn=generate_spectrogram_audio_and_loop,
                    title="Audio Diffusion",
                    description="Generate audio using Huggingface diffusers.\
        This takes about 20 minutes without a GPU, so why not make yourself a \
            cup of tea in the meantime? (Or try the teticio/audio-diffusion-ddim-256 \
                model which is faster.)",
                    inputs=[
                        gr.Dropdown(label="Model",
                                    choices=[
                                        "teticio/audio-diffusion-256",
                                        "teticio/audio-diffusion-breaks-256",
                                        "teticio/audio-diffusion-instrumental-hiphop-256",
                                        "teticio/audio-diffusion-ddim-256"
                                    ],
                                    value="teticio/audio-diffusion-256")
                    ],
                    outputs=[
                        gr.Image(label="Mel spectrogram", image_mode="L"),
                        gr.Audio(label="Audio"),
                        gr.Audio(label="Loop"),
                    ],
                    allow_flagging="never")

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--port", type=int)
    parser.add_argument("--server", type=int)
    args = parser.parse_args()
    demo.launch(server_name=args.server or "0.0.0.0", server_port=args.port)