File size: 8,230 Bytes
ce3fc4b
 
 
1892f86
9f59b48
ce3fc4b
ec9dc17
ce3fc4b
 
 
 
1892f86
 
 
 
 
 
 
 
 
 
ce3fc4b
 
589dfd0
2adbf1a
 
907cafc
40c455d
5b452a4
40c455d
907cafc
2709ff4
2adbf1a
2709ff4
2adbf1a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2709ff4
 
2adbf1a
 
 
 
 
9f59b48
 
 
 
 
 
2adbf1a
 
 
9f59b48
1892f86
ce3fc4b
 
 
9f59b48
 
09b3ba3
ce3fc4b
 
9f59b48
 
 
589dfd0
 
 
 
 
 
 
 
9f59b48
 
589dfd0
9f59b48
 
589dfd0
 
 
 
 
 
 
 
 
9f59b48
 
589dfd0
9f59b48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
import numpy as np
import gradio as gr
from bark import SAMPLE_RATE, generate_audio, preload_models
from bark.generation import SUPPORTED_LANGS
from share_btn import community_icon_html, loading_icon_html, share_js

DEBUG_MODE = False

if not DEBUG_MODE:
    _ = preload_models()

AVAILABLE_PROMPTS = ["Unconditional", "Announcer"]
PROMPT_LOOKUP = {}
for _, lang in SUPPORTED_LANGS:
    for n in range(10):
        label = f"Speaker {n} ({lang})"
        AVAILABLE_PROMPTS.append(label)
        PROMPT_LOOKUP[label] = f"{lang}_speaker_{n}"
PROMPT_LOOKUP["Unconditional"] = None
PROMPT_LOOKUP["Announcer"] = "announcer"

default_text = "Hello, my name is Suno. And, uh — and I like pizza. [laughs]\nBut I also have other interests such as playing tic tac toe."

title = "# 🐶 Bark</div>"

description = """
<div>
<a style="display:inline-block" href='https://github.com/suno-ai/bark'><img src='https://img.shields.io/github/stars/suno-ai/bark?style=social' /></a>
<a style='display:inline-block' href='https://discord.gg/J2B2vsjKuE'><img src='https://dcbadge.vercel.app/api/server/J2B2vsjKuE?compact=true&style=flat' /></a>
<a style="display:inline-block; margin-left: 1em" href="https://huggingface.co/spaces/suno/bark?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space%20to%20skip%20the%20queue-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a>
</div>
Bark is a universal text-to-audio model created by <a href="www.suno.ai">Suno</a>, with code publicly available <a href="https://github.com/suno-ai/bark">here</a>. \
Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. \
This demo should be used for research purposes only. \
The model output is not censored and the authors do not endorse the opinions in the generated content. \
Use at your own risk.
"""

article = """

## 🌎 Foreign Language

Bark supports various languages out-of-the-box and automatically determines language from input text. \
When prompted with code-switched text, Bark will even attempt to employ the native accent for the respective languages in the same voice.

Try the prompt:

```
Buenos días Miguel. Tu colega piensa que tu alemán es extremadamente malo. But I suppose your english isn't terrible.
```

## 🤭 Non-Speech Sounds

Below is a list of some known non-speech sounds, but we are finding more every day. \
Please let us know if you find patterns that work particularly well on Discord!

* [laughter]
* [laughs]
* [sighs]
* [music]
* [gasps]
* [clears throat]
* — or ... for hesitations
* ♪ for song lyrics
* capitalization for emphasis of a word
* MAN/WOMAN: for bias towards speaker

Try the prompt:

```
" [clears throat] Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as... ♪ singing ♪."
```

## 🎶 Music
Bark can generate all types of audio, and, in principle, doesn't see a difference between speech and music. \
Sometimes Bark chooses to generate text as music, but you can help it out by adding music notes around your lyrics.

Try the prompt:

```
♪ In the jungle, the mighty jungle, the lion barks tonight ♪
```

## 🧬 Voice Cloning

Bark has the capability to fully clone voices - including tone, pitch, emotion and prosody. \
The model also attempts to preserve music, ambient noise, etc. from input audio. \
However, to mitigate misuse of this technology, we limit the audio history prompts to a limited set of Suno-provided, fully synthetic options to choose from.

## 👥 Speaker Prompts

You can provide certain speaker prompts such as NARRATOR, MAN, WOMAN, etc. \
Please note that these are not always respected, especially if a conflicting audio history prompt is given.

Try the prompt:

```
WOMAN: I would like an oatmilk latte please.
MAN: Wow, that's expensive!
```

## Details

Bark model by <a href="www.suno.ai">Suno</a>, including official <a href="https://github.com/suno-ai/bark">code</a> and model weights. \
Gradio demo supported by 🤗 Hugging Face. Bark is licensed under the MIT license, see details on <a href="https://github.com/suno-ai/bark">GitHub</a>.


"""

examples = [
    ["Please surprise me and speak in whatever voice you enjoy. Vielen Dank und Gesundheit!",
        "Unconditional"],  # , 0.7, 0.7],
    ["Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.",
        "Speaker 1 (en)"],  # , 0.7, 0.7],
    ["Buenos días Miguel. Tu colega piensa que tu alemán es extremadamente malo. But I suppose your english isn't terrible.",
        "Speaker 0 (es)"],  # , 0.7, 0.7],
]


def gen_tts(text, history_prompt):  # , temp_semantic, temp_waveform):
    history_prompt = PROMPT_LOOKUP[history_prompt]
    if DEBUG_MODE:
        audio_arr = np.zeros(SAMPLE_RATE)
    else:
        # , text_temp=temp_semantic, waveform_temp=temp_waveform)
        audio_arr = generate_audio(text, history_prompt=history_prompt)
    audio_arr = (audio_arr * 32767).astype(np.int16)
    return (SAMPLE_RATE, audio_arr)


css = """
        #share-btn-container {
            display: flex;
            padding-left: 0.5rem !important;
            padding-right: 0.5rem !important;
            background-color: #000000;
            justify-content: center;
            align-items: center;
            border-radius: 9999px !important; 
            width: 13rem;
            margin-top: 10px;
            margin-left: auto;
            flex: unset !important;
        }
        #share-btn {
            all: initial;
            color: #ffffff;
            font-weight: 600;
            cursor: pointer;
            font-family: 'IBM Plex Sans', sans-serif;
            margin-left: 0.5rem !important;
            padding-top: 0.25rem !important;
            padding-bottom: 0.25rem !important;
            right:0;
        }
        #share-btn * {
            all: unset !important;
        }
        #share-btn-container div:nth-child(-n+2){
            width: auto !important;
            min-height: 0px !important;
        }
        #share-btn-container .wrap {
            display: none !important;
        }
"""
with gr.Blocks(css=css) as block:
    gr.Markdown(title)
    gr.Markdown(description)
    with gr.Row():
        with gr.Column():
            input_text = gr.Textbox(
                label="Input Text", lines=2, value=default_text, elem_id="input_text")
            options = gr.Dropdown(
                AVAILABLE_PROMPTS, value="Speaker 1 (en)", label="Acoustic Prompt", elem_id="speaker_option")
            run_button = gr.Button(text="Generate Audio", type="button")
        with gr.Column():
            audio_out = gr.Audio(label="Generated Audio",
                                 type="numpy", elem_id="audio_out")
            with gr.Row(visible=False) as share_row:
                with gr.Group(elem_id="share-btn-container"):
                    community_icon = gr.HTML(community_icon_html)
                    loading_icon = gr.HTML(loading_icon_html)
                    share_button = gr.Button(
                        "Share to community", elem_id="share-btn")
                    share_button.click(None, [], [], _js=share_js)
    inputs = [input_text, options]
    outputs = [audio_out]
    gr.Examples(examples=examples, fn=gen_tts, inputs=inputs,
                outputs=outputs, cache_examples=True)
    gr.Markdown(article)
    run_button.click(fn=lambda: gr.update(visible=False), inputs=None, outputs=share_row, queue=False).then(
        fn=gen_tts, inputs=inputs, outputs=outputs, queue=True).then(
        fn=lambda: gr.update(visible=True), inputs=None, outputs=share_row, queue=False)

block.queue()
block.launch()