text-generation-webui/extensions/silero_tts/test_tts.py

import time
from pathlib import Path

import torch
import tts_preprocessor

torch._C._jit_set_profiling_mode(False)


params = {
    'activate': True,
    'speaker': 'en_49',
    'language': 'en',
    'model_id': 'v3_en',
    'sample_rate': 48000,
    'device': 'cpu',
    'show_text': True,
    'autoplay': True,
    'voice_pitch': 'medium',
    'voice_speed': 'medium',
}

current_params = params.copy()
voices_by_gender = ['en_99', 'en_45', 'en_18', 'en_117', 'en_49', 'en_51', 'en_68', 'en_0', 'en_26', 'en_56', 'en_74', 'en_5', 'en_38', 'en_53', 'en_21', 'en_37', 'en_107', 'en_10', 'en_82', 'en_16', 'en_41', 'en_12', 'en_67', 'en_61', 'en_14', 'en_11', 'en_39', 'en_52', 'en_24', 'en_97', 'en_28', 'en_72', 'en_94', 'en_36', 'en_4', 'en_43', 'en_88', 'en_25', 'en_65', 'en_6', 'en_44', 'en_75', 'en_91', 'en_60', 'en_109', 'en_85', 'en_101', 'en_108', 'en_50', 'en_96', 'en_64', 'en_92', 'en_76', 'en_33', 'en_116', 'en_48', 'en_98', 'en_86', 'en_62', 'en_54', 'en_95', 'en_55', 'en_111', 'en_3', 'en_83', 'en_8', 'en_47', 'en_59', 'en_1', 'en_2', 'en_7', 'en_9', 'en_13', 'en_15', 'en_17', 'en_19', 'en_20', 'en_22', 'en_23', 'en_27', 'en_29', 'en_30', 'en_31', 'en_32', 'en_34', 'en_35', 'en_40', 'en_42', 'en_46', 'en_57', 'en_58', 'en_63', 'en_66', 'en_69', 'en_70', 'en_71', 'en_73', 'en_77', 'en_78', 'en_79', 'en_80', 'en_81', 'en_84', 'en_87', 'en_89', 'en_90', 'en_93', 'en_100', 'en_102', 'en_103', 'en_104', 'en_105', 'en_106', 'en_110', 'en_112', 'en_113', 'en_114', 'en_115']
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():
    model, example_text = torch.hub.load(repo_or_dir='snakers4/silero-models', model='silero_tts', language=params['language'], speaker=params['model_id'])
    model.to(params['device'])
    return model


model = load_model()


def output_modifier(string):
    """
    This function is applied to the model outputs.
    """

    global model, current_params

    original_string = string
    string = tts_preprocessor.preprocess(string)
    processed_string = string

    if string == '':
        string = '*Empty reply, try regenerating*'
    else:
        output_file = Path(f'extensions/silero_tts/outputs/test_{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}\n\nProcessed:\n{processed_string}'

    print(string)


if __name__ == '__main__':
    import sys
    output_modifier(sys.argv[1])