File size: 9,237 Bytes
a01f2fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
import html
import json
import random
import time
from pathlib import Path

import gradio as gr
import torch

from extensions.silero_tts import tts_preprocessor
from modules import chat, shared, ui_chat
from modules.utils import gradio

torch._C._jit_set_profiling_mode(False)


params = {
    'activate': True,
    'speaker': 'en_56',
    'language': 'English',
    'model_id': 'v3_en',
    'sample_rate': 48000,
    'device': 'cpu',
    'show_text': False,
    'autoplay': True,
    'voice_pitch': 'medium',
    'voice_speed': 'medium',
    'local_cache_path': ''  # User can override the default cache path to something other via settings.json
}

current_params = params.copy()

with open(Path("extensions/silero_tts/languages.json"), encoding='utf8') as f:
    languages = json.load(f)

voice_pitches = ['x-low', 'low', 'medium', 'high', 'x-high']
voice_speeds = ['x-slow', 'slow', 'medium', 'fast', 'x-fast']

# Used for making text xml compatible, needed for voice pitch and speed control
table = str.maketrans({
    "<": "&lt;",
    ">": "&gt;",
    "&": "&amp;",
    "'": "&apos;",
    '"': "&quot;",
})


def xmlesc(txt):
    return txt.translate(table)


def load_model():
    torch_cache_path = torch.hub.get_dir() if params['local_cache_path'] == '' else params['local_cache_path']
    model_path = torch_cache_path + "/snakers4_silero-models_master/src/silero/model/" + params['model_id'] + ".pt"
    if Path(model_path).is_file():
        print(f'\nUsing Silero TTS cached checkpoint found at {torch_cache_path}')
        model, example_text = torch.hub.load(repo_or_dir=torch_cache_path + '/snakers4_silero-models_master/', model='silero_tts', language=languages[params['language']]["lang_id"], speaker=params['model_id'], source='local', path=model_path, force_reload=True)
    else:
        print(f'\nSilero TTS cache not found at {torch_cache_path}. Attempting to download...')
        model, example_text = torch.hub.load(repo_or_dir='snakers4/silero-models', model='silero_tts', language=languages[params['language']]["lang_id"], speaker=params['model_id'])
    model.to(params['device'])
    return model


def remove_tts_from_history(history):
    for i, entry in enumerate(history['internal']):
        history['visible'][i] = [history['visible'][i][0], entry[1]]

    return history


def toggle_text_in_history(history):
    for i, entry in enumerate(history['visible']):
        visible_reply = entry[1]
        if visible_reply.startswith('<audio'):
            if params['show_text']:
                reply = history['internal'][i][1]
                history['visible'][i] = [history['visible'][i][0], f"{visible_reply.split('</audio>')[0]}</audio>\n\n{reply}"]
            else:
                history['visible'][i] = [history['visible'][i][0], f"{visible_reply.split('</audio>')[0]}</audio>"]

    return history


def state_modifier(state):
    if not params['activate']:
        return state

    state['stream'] = False
    return state


def input_modifier(string, state):
    if not params['activate']:
        return string

    shared.processing_message = "*Is recording a voice message...*"
    return string


def history_modifier(history):
    # Remove autoplay from the last reply
    if len(history['internal']) > 0:
        history['visible'][-1] = [
            history['visible'][-1][0],
            history['visible'][-1][1].replace('controls autoplay>', 'controls>')
        ]

    return history


def output_modifier(string, state):
    global model, current_params, streaming_state

    for i in params:
        if params[i] != current_params[i]:
            model = load_model()
            current_params = params.copy()
            break

    if not params['activate']:
        return string

    original_string = string

    string = tts_preprocessor.preprocess(html.unescape(string))

    if string == '':
        string = '*Empty reply, try regenerating*'
    else:
        output_file = Path(f'extensions/silero_tts/outputs/{state["character_menu"]}_{int(time.time())}.wav')
        prosody = '<prosody rate="{}" pitch="{}">'.format(params['voice_speed'], params['voice_pitch'])
        silero_input = f'<speak>{prosody}{xmlesc(string)}</prosody></speak>'
        model.save_wav(ssml_text=silero_input, speaker=params['speaker'], sample_rate=int(params['sample_rate']), audio_path=str(output_file))

        autoplay = 'autoplay' if params['autoplay'] else ''
        string = f'<audio src="file/{output_file.as_posix()}" controls {autoplay}></audio>'
        if params['show_text']:
            string += f'\n\n{original_string}'

    shared.processing_message = "*Is typing...*"
    return string


def setup():
    global model
    model = load_model()


def random_sentence():
    with open(Path("extensions/silero_tts/harvard_sentences.txt")) as f:
        return random.choice(list(f))


def voice_preview(string):
    global model, current_params, streaming_state

    for i in params:
        if params[i] != current_params[i]:
            model = load_model()
            current_params = params.copy()
            break

    string = tts_preprocessor.preprocess(string or random_sentence())

    output_file = Path('extensions/silero_tts/outputs/voice_preview.wav')
    prosody = f"<prosody rate=\"{params['voice_speed']}\" pitch=\"{params['voice_pitch']}\">"
    silero_input = f'<speak>{prosody}{xmlesc(string)}</prosody></speak>'
    model.save_wav(ssml_text=silero_input, speaker=params['speaker'], sample_rate=int(params['sample_rate']), audio_path=str(output_file))

    return f'<audio src="file/{output_file.as_posix()}?{int(time.time())}" controls autoplay></audio>'


def language_change(lang):
    global params
    params.update({"language": lang, "speaker": languages[lang]["default_voice"], "model_id": languages[lang]["model_id"]})
    return gr.update(choices=languages[lang]["voices"], value=languages[lang]["default_voice"])


def custom_css():
    path_to_css = Path(__file__).parent.resolve() / 'style.css'
    return open(path_to_css, 'r').read()


def ui():
    # Gradio elements
    with gr.Accordion("Silero TTS"):
        with gr.Row():
            activate = gr.Checkbox(value=params['activate'], label='Activate TTS')
            autoplay = gr.Checkbox(value=params['autoplay'], label='Play TTS automatically')

        show_text = gr.Checkbox(value=params['show_text'], label='Show message text under audio player')
        
        with gr.Row():
            language = gr.Dropdown(value=params['language'], choices=sorted(languages.keys()), label='Language')
            voice = gr.Dropdown(value=params['speaker'], choices=languages[params['language']]["voices"], label='TTS voice')
        with gr.Row():
            v_pitch = gr.Dropdown(value=params['voice_pitch'], choices=voice_pitches, label='Voice pitch')
            v_speed = gr.Dropdown(value=params['voice_speed'], choices=voice_speeds, label='Voice speed')

        with gr.Row():
            preview_text = gr.Text(show_label=False, placeholder="Preview text", elem_id="silero_preview_text")
            preview_play = gr.Button("Preview")
            preview_audio = gr.HTML(visible=False)

        with gr.Row():
            convert = gr.Button('Permanently replace audios with the message texts')
            convert_cancel = gr.Button('Cancel', visible=False)
            convert_confirm = gr.Button('Confirm (cannot be undone)', variant="stop", visible=False)

    # Convert history with confirmation
    convert_arr = [convert_confirm, convert, convert_cancel]
    convert.click(lambda: [gr.update(visible=True), gr.update(visible=False), gr.update(visible=True)], None, convert_arr)
    convert_confirm.click(
        lambda: [gr.update(visible=False), gr.update(visible=True), gr.update(visible=False)], None, convert_arr).then(
        remove_tts_from_history, gradio('history'), gradio('history')).then(
        chat.save_history, gradio('history', 'unique_id', 'character_menu', 'mode'), None).then(
        chat.redraw_html, gradio(ui_chat.reload_arr), gradio('display'))

    convert_cancel.click(lambda: [gr.update(visible=False), gr.update(visible=True), gr.update(visible=False)], None, convert_arr)

    # Toggle message text in history
    show_text.change(
        lambda x: params.update({"show_text": x}), show_text, None).then(
        toggle_text_in_history, gradio('history'), gradio('history')).then(
        chat.save_history, gradio('history', 'unique_id', 'character_menu', 'mode'), None).then(
        chat.redraw_html, gradio(ui_chat.reload_arr), gradio('display'))

    # Event functions to update the parameters in the backend
    activate.change(lambda x: params.update({"activate": x}), activate, None)
    autoplay.change(lambda x: params.update({"autoplay": x}), autoplay, None)
    language.change(language_change, language, voice, show_progress=False)
    voice.change(lambda x: params.update({"speaker": x}), voice, None)
    v_pitch.change(lambda x: params.update({"voice_pitch": x}), v_pitch, None)
    v_speed.change(lambda x: params.update({"voice_speed": x}), v_speed, None)

    # Play preview
    preview_text.submit(voice_preview, preview_text, preview_audio)
    preview_play.click(voice_preview, preview_text, preview_audio)