File size: 3,037 Bytes
194fffd
 
 
fc50d18
 
194fffd
 
142fdc7
 
 
 
 
 
 
194fffd
142fdc7
 
0dfedcd
194fffd
 
fc50d18
194fffd
e1c65f1
533ef97
 
 
 
 
 
 
e1c65f1
 
 
 
 
 
 
3444a7f
 
 
 
 
 
0dfedcd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
194fffd
 
 
142fdc7
 
 
e0c1684
142fdc7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0dfedcd
142fdc7
 
 
262bc3f
142fdc7
e0c1684
142fdc7
194fffd
 
533ef97
0dfedcd
194fffd
 
cff1c92
3444a7f
0dfedcd
96f76e3
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
import gradio as gr
from TTS.api import TTS

tts = TTS("tts_models/multilingual/multi-dataset/xtts_v1")
tts.to("cuda")


def predict(prompt, language, audio_file_pth):
    tts.tts_to_file(
        text=prompt,
        file_path="output.wav",
        speaker_wav=audio_file_pth,
        language=language,
    )

    return gr.make_waveform(
        audio="output.wav",
    ), gr.Audio(value="output.wav")


title = "Coqui🐸 XTTS"

description = """
XTTS is a Voice generation model that lets you clone voices into different languages by using just a quick 3-second audio clip. 
<br/>
Built on Tortoise, XTTS has important model changes that make cross-language voice cloning and multi-lingual speech generation super easy. 
<br/>
This is the same model that powers Coqui Studio, and Coqui API, however we apply a few tricks to make it faster and support streaming inference.
<br/>
<br/>
<p>For faster inference without waiting in the queue, you should duplicate this space and upgrade to GPU via the settings.
<br/>
<a href="https://huggingface.co./spaces/coqui/xtts?duplicate=true">
<img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
</p>
"""

article = """
<div style='margin:20px auto;'>
<p>By using this demo you agree to the terms of the Coqui Public Model License at https://coqui.ai/cpml</p>
</div>
"""

examples = [
    [
        "Once when I was six years old I saw a magnificent picture.",
        "en",
        "examples/female.wav",
    ],
    [
        "Lorsque j'avais six ans j'ai vu, une fois, une magnifique image.",
        "fr",
        "examples/male.wav",
    ],
    [
        "Un tempo lontano, quando avevo sei anni, vidi un magnifico disegno.",
        "it",
        "examples/female.wav",
    ],
]

gr.Interface(
    fn=predict,
    inputs=[
        gr.Textbox(
            label="Text Prompt",
            info="One or two sentences at a time is better",
            value="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
        ),
        gr.Dropdown(
            label="Language",
            info="Select an output language for the synthesised speech",
            choices=[
                "en",
                "es",
                "fr",
                "de",
                "it",
                "pt",
                "pl",
                "tr",
                "ru",
                "nl",
                "cz",
                "ar",
                "zh",
            ],
            max_choices=1,
            value="en",
        ),
        gr.Audio(
            label="Reference Audio",
            info="Click on the ✎ button to upload your own target speaker audio",
            type="filepath",
            value="examples/female.wav",
        ),
    ],
    outputs=[
        gr.Video(label="Synthesised Waveform"),
        gr.Audio(label="Synthesised Audio"),
    ],
    title=title,
    description=description,
    article=article,
    examples=examples,
).queue().launch(debug=True)