File size: 6,953 Bytes
b4aec50
 
 
 
 
 
 
 
 
 
 
 
fdffacd
b4aec50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37952eb
 
 
 
 
b4aec50
2301775
 
a7ff543
 
0a02aec
b4aec50
 
 
357e299
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37952eb
b4aec50
 
2301775
 
b4aec50
37952eb
b4aec50
 
2301775
b4aec50
770531a
a664672
b4aec50
0b4abe8
fc12492
3d974c0
cf3c7a3
 
c285708
cf3c7a3
 
fa2eee3
a664672
cf3c7a3
a664672
770531a
37952eb
770531a
37952eb
770531a
37952eb
b4aec50
0b4abe8
b4aec50
 
 
 
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
import gradio as gr
import json
import torch
import wavio
from tqdm import tqdm
from huggingface_hub import snapshot_download
from models import AudioDiffusion, DDPMScheduler
from audioldm.audio.stft import TacotronSTFT
from audioldm.variational_autoencoder import AutoencoderKL
from gradio import Markdown

class Tango:
    def __init__(self, name="declare-lab/tango-full-ft-audiocaps", device="cuda:0"):
        
        path = snapshot_download(repo_id=name)
        
        vae_config = json.load(open("{}/vae_config.json".format(path)))
        stft_config = json.load(open("{}/stft_config.json".format(path)))
        main_config = json.load(open("{}/main_config.json".format(path)))
        
        self.vae = AutoencoderKL(**vae_config).to(device)
        self.stft = TacotronSTFT(**stft_config).to(device)
        self.model = AudioDiffusion(**main_config).to(device)
        
        vae_weights = torch.load("{}/pytorch_model_vae.bin".format(path), map_location=device)
        stft_weights = torch.load("{}/pytorch_model_stft.bin".format(path), map_location=device)
        main_weights = torch.load("{}/pytorch_model_main.bin".format(path), map_location=device)
        
        self.vae.load_state_dict(vae_weights)
        self.stft.load_state_dict(stft_weights)
        self.model.load_state_dict(main_weights)

        print ("Successfully loaded checkpoint from:", name)
        
        self.vae.eval()
        self.stft.eval()
        self.model.eval()
        
        self.scheduler = DDPMScheduler.from_pretrained(main_config["scheduler_name"], subfolder="scheduler")
        
    def chunks(self, lst, n):
        """ Yield successive n-sized chunks from a list. """
        for i in range(0, len(lst), n):
            yield lst[i:i + n]
        
    def generate(self, prompt, steps=100, guidance=3, samples=1, disable_progress=True):
        """ Genrate audio for a single prompt string. """
        with torch.no_grad():
            latents = self.model.inference([prompt], self.scheduler, steps, guidance, samples, disable_progress=disable_progress)
            mel = self.vae.decode_first_stage(latents)
            wave = self.vae.decode_to_waveform(mel)
        return wave[0]
    
    def generate_for_batch(self, prompts, steps=200, guidance=3, samples=1, batch_size=8, disable_progress=True):
        """ Genrate audio for a list of prompt strings. """
        outputs = []
        for k in tqdm(range(0, len(prompts), batch_size)):
            batch = prompts[k: k+batch_size]
            with torch.no_grad():
                latents = self.model.inference(batch, self.scheduler, steps, guidance, samples, disable_progress=disable_progress)
                mel = self.vae.decode_first_stage(latents)
                wave = self.vae.decode_to_waveform(mel)
                outputs += [item for item in wave]
        if samples == 1:
            return outputs
        else:
            return list(self.chunks(outputs, samples))

# Initialize TANGO
if torch.cuda.is_available():
    tango = Tango()
else:
    tango = Tango(device="cpu")

def gradio_generate(prompt, steps, guidance):
    output_wave = tango.generate(prompt, steps, guidance)
    # output_filename = f"{prompt.replace(' ', '_')}_{steps}_{guidance}"[:250] + ".wav"
    output_filename = "temp.wav"
    wavio.write(output_filename, output_wave, rate=16000, sampwidth=2)
    
    return output_filename

# description_text = """
# <p><a href="https://huggingface.co/spaces/declare-lab/tango/blob/main/app.py?duplicate=true"> <img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a> For faster inference without waiting in queue, you may duplicate the space and upgrade to a GPU in the settings. <br/><br/>
# Generate audio using TANGO by providing a text prompt.
# <br/><br/>Limitations: TANGO is trained on the small AudioCaps dataset so it may not generate good audio \
# samples related to concepts that it has not seen in training (e.g. singing). For the same reason, TANGO \
# is not always able to finely control its generations over textual control prompts. For example, \
# the generations from TANGO for prompts Chopping tomatoes on a wooden table and Chopping potatoes \
# on a metal table are very similar. \
# <br/><br/>We are currently training another version of TANGO on larger datasets to enhance its generalization, \
# compositional and controllable generation ability.
# <br/><br/>We recommend using a guidance scale of 3. The default number of steps is set to 100. More steps generally lead to better quality of generated audios but will take longer.
# <br/><br/>
# <h1> ChatGPT-enhanced audio generation</h1>
# <br/>
# As TANGO consists of an instruction-tuned LLM, it is able to process complex sound descriptions allowing us to provide more detailed instructions to improve the generation quality.
# For example, ``A boat is moving on the sea'' vs ``The sound of the water lapping against the hull of the boat or splashing as you move through the waves''. The latter is obtained by prompting ChatGPT to explain the sound generated when a boat moves on the sea.
# Using this ChatGPT-generated description of the sound, TANGO provides superior results.
# <p/>
# """
description_text = ""
# Gradio input and output components
input_text = gr.inputs.Textbox(lines=2, label="Prompt")
output_audio = gr.outputs.Audio(label="Generated Audio", type="filepath")
denoising_steps = gr.Slider(minimum=100, maximum=200, value=100, step=1, label="Steps", interactive=True)
guidance_scale = gr.Slider(minimum=1, maximum=10, value=3, step=0.1, label="Guidance Scale", interactive=True)

# Gradio interface
gr_interface = gr.Interface(
    fn=gradio_generate,
    inputs=[input_text, denoising_steps, guidance_scale],
    outputs=[output_audio],
    title="TANGO: Text to Audio using Instruction-Guided Diffusion",
    description=description_text,
    allow_flagging=False,
    examples=[
        ["A lady is singing a song with a kid"],
        ["The sound of the water lapping against the hull of the boat or splashing as you move through the waves"],
        ["An audience cheering and clapping"],
        ["Rolling thunder with lightning strikes"],
        ["Gentle water stream, birds chirping and sudden gun shot"],
        ["A car engine revving"],
        ["A dog barking"],
        ["A cat meowing"],
        ["Wooden table tapping sound while water pouring"],
        ["Emergency sirens wailing"],
        ["two gunshots followed by birds flying away while chirping"],
        ["Whistling with birds chirping"],
        ["A person snoring"],
        ["Motor vehicles are driving with loud engines and a person whistles"],
        ["People cheering in a stadium while thunder and lightning strikes"],
        ["A helicopter is in flight"],
        ["A dog barking and a man talking and a racing car passes by"],
    ],
    cache_examples=False,
)

# Launch Gradio app
gr_interface.launch()