More silero languages (#3950)
This commit is contained in:
missionfloyd
GitHub
parent
db7ecdd274
commit
c0ffb77fd8
2 changed files with 189 additions and 27 deletions
|
|
@ -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"<prosody rate=\"{params['voice_speed']}\" pitch=\"{params['voice_pitch']}\">"
|
||||
|
|
@ -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')
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue