From c0ffb77fd8471c1cade593879d17d2e817a1ed0b Mon Sep 17 00:00:00 2001 From: missionfloyd Date: Mon, 16 Oct 2023 14:12:32 -0600 Subject: [PATCH] More silero languages (#3950) --- extensions/silero_tts/languages.json | 176 +++++++++++++++++++++++++++ extensions/silero_tts/script.py | 40 ++---- 2 files changed, 189 insertions(+), 27 deletions(-) create mode 100644 extensions/silero_tts/languages.json diff --git a/extensions/silero_tts/languages.json b/extensions/silero_tts/languages.json new file mode 100644 index 00000000..3e7f2af7 --- /dev/null +++ b/extensions/silero_tts/languages.json @@ -0,0 +1,176 @@ +{ + "English": { + "lang_id": "en", + "voices": ["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"], + "default_voice": "en_56", + "model_id": "v3_en" + }, + "Spanish": { + "lang_id": "es", + "voices": ["es_0", "es_1", "es_2"], + "default_voice": "es_0", + "model_id": "v3_es" + }, + "French": { + "lang_id": "fr", + "voices": ["fr_0", "fr_1", "fr_2", "fr_3", "fr_4", "fr_5"], + "default_voice": "fr_0", + "model_id": "v3_fr" + }, + "German": { + "lang_id": "de", + "voices": ["bernd_ungerer", "eva_k", "friedrich", "hokuspokus", "karlsson"], + "default_voice": "eva_k", + "model_id": "v3_de" + }, + "Russian": { + "lang_id": "ru", + "voices": ["aidar", "baya", "kseniya", "xenia"], + "default_voice": "aidar", + "model_id": "ru_v3" + }, + "Tatar": { + "lang_id": "tt", + "voices": ["dilyara"], + "default_voice": "dilyara", + "model_id": "v3_tt" + }, + "Ukranian": { + "lang_id": "ua", + "voices": ["mykyta"], + "default_voice": "mykyta", + "model_id": "v3_ua" + }, + "Uzbek": { + "lang_id": "uz", + "voices": ["dilnavoz"], + "default_voice": "dilnavoz", + "model_id": "v3_uz" + }, + "English (India)": { + "lang_id": "en", + "voices": ["tamil_female", "bengali_female", "malayalam_male", "manipuri_female", "assamese_female", "gujarati_male", "telugu_male", "kannada_male", "hindi_female", "rajasthani_female", "kannada_female", "bengali_male", "tamil_male", "gujarati_female", "assamese_male"], + "default_voice": "hindi_female", + "model_id": "v3_en_indic" + }, + "Avar": { + "lang_id": "cyrillic", + "voices": ["b_ava"], + "default_voice": "b_ava", + "model_id": "v4_cyrillic" + }, + "Bashkir": { + "lang_id": "cyrillic", + "voices": ["b_bashkir"], + "default_voice": "b_bashkir", + "model_id": "v4_cyrillic" + }, + "Bulgarian": { + "lang_id": "cyrillic", + "voices": ["b_bulb", "b_bulc"], + "default_voice": "b_bulb", + "model_id": "v4_cyrillic" + }, + "Chechen": { + "lang_id": "cyrillic", + "voices": ["cv_ekaterina", "b_cv"], + "default_voice": "b_che", + "model_id": "v4_cyrillic" + }, + "Chuvash": { + "lang_id": "cyrillic", + "voices": ["b_che"], + "default_voice": "b_che", + "model_id": "v4_cyrillic" + }, + "Erzya": { + "lang_id": "cyrillic", + "voices": ["b_myv"], + "default_voice": "b_myv", + "model_id": "v4_cyrillic" + }, + "Kalmyk": { + "lang_id": "cyrillic", + "voices": ["b_kalmyk"], + "default_voice": "b_kalmyk", + "model_id": "v4_cyrillic" + }, + "Karachay-Balkar": { + "lang_id": "cyrillic", + "voices": ["b_krc"], + "default_voice": "b_krc", + "model_id": "v4_cyrillic" + }, + "Kazakh": { + "lang_id": "cyrillic", + "voices": ["kz_F1", "kz_F2", "kz_F3", "kz_M1", "kz_M1"], + "default_voice": "kz_F1", + "model_id": "v4_cyrillic" + }, + "Khakas": { + "lang_id": "cyrillic", + "voices": ["b_kjh"], + "default_voice": "b_kjh", + "model_id": "v4_cyrillic" + }, + "Komi-Ziryan": { + "lang_id": "cyrillic", + "voices": ["b_kpv"], + "default_voice": "b_kpv", + "model_id": "v4_cyrillic" + }, + "Lezghian": { + "lang_id": "cyrillic", + "voices": ["b_lez"], + "default_voice": "b_lez", + "model_id": "v4_cyrillic" + }, + "Mari": { + "lang_id": "cyrillic", + "voices": ["b_mhr"], + "default_voice": "b_mhr", + "model_id": "v4_cyrillic" + }, + "Mari High": { + "lang_id": "cyrillic", + "voices": ["b_mrj"], + "default_voice": "b_mrj", + "model_id": "v4_cyrillic" + }, + "Nogai": { + "lang_id": "cyrillic", + "voices": ["b_nog"], + "default_voice": "b_nog", + "model_id": "v4_cyrillic" + }, + "Ossetic": { + "lang_id": "cyrillic", + "voices": ["b_oss"], + "default_voice": "b_nog", + "model_id": "v4_cyrillic" + }, + "Tuvinian": { + "lang_id": "cyrillic", + "voices": ["b_tyv"], + "default_voice": "b_tyv", + "model_id": "v4_cyrillic" + }, + "Udmurt": { + "lang_id": "cyrillic", + "voices": ["b_udm"], + "default_voice": "b_udm", + "model_id": "v4_cyrillic" + }, + "Yakut": { + "lang_id": "cyrillic", + "voices": ["b_sah"], + "default_voice": "b_sah", + "model_id": "v4_cyrillic" + }, + "Kalmyk": { + "lang_id": "cyrillic", + "voices": ["kalmyk_delghir", "kalmyk_erdni"], + "default_voice": "kalmyk_delghir", + "model_id": "v4_cyrillic" + } +} diff --git a/extensions/silero_tts/script.py b/extensions/silero_tts/script.py index e4bacc72..234338dd 100644 --- a/extensions/silero_tts/script.py +++ b/extensions/silero_tts/script.py @@ -1,4 +1,5 @@ import html +import json import random import time from pathlib import Path @@ -16,7 +17,7 @@ torch._C._jit_set_profiling_mode(False) params = { 'activate': True, 'speaker': 'en_56', - 'language': 'en', + 'language': 'English', 'model_id': 'v3_en', 'sample_rate': 48000, 'device': 'cpu', @@ -29,23 +30,8 @@ params = { current_params = params.copy() -voices_en = ['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'] -voices_es = ["es_0", "es_1", "es_2"] -voices_fr = ["fr_0", "fr_1", "fr_2", "fr_3", "fr_4", "fr_5"] -voices_de = ["bernd_ungerer", "eva_k", "friedrich", "hokuspokus", "karlsson"] -voices_ru = ["aidar", "baya", "kseniya", "xenia"] -voices_ua = ["mykyta"] -voices_uz = ["dilnavoz"] - -languages = { - "en": {"label": "English", "voices": voices_en, "default_voice": "en_56", "model_id": "v3_en"}, - "es": {"label": "Español", "voices": voices_es, "default_voice": "es_0", "model_id": "v3_es"}, - "fr": {"label": "Français", "voices": voices_fr, "default_voice": "fr_0", "model_id": "v3_fr"}, - "de": {"label": "Deutsch", "voices": voices_de, "default_voice": "eva_k", "model_id": "v3_de"}, - "ru": {"label": "русский", "voices": voices_ru, "default_voice": "aidar", "model_id": "ru_v3"}, - "ua": {"label": "українська", "voices": voices_ua, "default_voice": "mykyta", "model_id": "v3_ua"}, - "uz": {"label": "Oʻzbekcha", "voices": voices_uz, "default_voice": "dilnavoz", "model_id": "v3_uz"}, -} +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'] @@ -69,10 +55,10 @@ def load_model(): 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=params['language'], speaker=params['model_id'], source='local', path=model_path, force_reload=True) + 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=params['language'], speaker=params['model_id']) + 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 @@ -137,6 +123,7 @@ def output_modifier(string, state): return string original_string = string + string = tts_preprocessor.preprocess(html.unescape(string)) if string == '': @@ -166,7 +153,7 @@ def random_sentence(): return random.choice(list(f)) -def voice_preview(preview_text): +def voice_preview(string): global model, current_params, streaming_state for i in params: @@ -175,7 +162,7 @@ def voice_preview(preview_text): current_params = params.copy() break - string = tts_preprocessor.preprocess(preview_text or random_sentence()) + string = tts_preprocessor.preprocess(string or random_sentence()) output_file = Path('extensions/silero_tts/outputs/voice_preview.wav') prosody = f"" @@ -187,9 +174,8 @@ def voice_preview(preview_text): def language_change(lang): global params - lang_code = list(languages.keys())[lang] - params.update({"language": lang_code, "speaker": languages[lang_code]["default_voice"], "model_id": languages[lang_code]["model_id"]}) - return gr.update(choices=languages[lang_code]["voices"], value=languages[lang_code]["default_voice"]) + 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(): @@ -207,8 +193,8 @@ def ui(): show_text = gr.Checkbox(value=params['show_text'], label='Show message text under audio player') with gr.Row(): - language = gr.Dropdown(value=languages[params['language']]["label"], choices=[v["label"] for _, v in languages.items()], label='Language', type="index") - voice = gr.Dropdown(value=params['speaker'], choices=voices_en, label='TTS voice') + 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')