MeloTTS / app.py
mrfakename's picture
Update app.py
70cbf96 verified
raw
history blame
2.84 kB
# WebUI by mrfakename <X @realmrfakename / HF @mrfakename>
# Demo also available on HF Spaces: https://huggingface.co/spaces/mrfakename/MeloTTS
import gradio as gr
import os, torch, io
os.system('python -m unidic download')
# print("Make sure you've downloaded unidic (python -m unidic download) for this WebUI to work.")
from melo.api import TTS
speed = 1.0
import tempfile
device = 'cuda'
models = {
'EN': TTS(language='EN', device=device),
'ES': TTS(language='ES', device=device),
'FR': TTS(language='FR', device=device),
'ZH': TTS(language='ZH', device=device),
'JP': TTS(language='JP', device=device),
'KR': TTS(language='KR', device=device),
}
speaker_ids = models['EN'].hps.data.spk2id
default_text_dict = {
'EN': 'The field of text-to-speech has seen rapid development recently.',
'ES': 'El campo de la conversión de texto a voz ha experimentado un rápido desarrollo recientemente.',
'FR': 'Le domaine de la synthèse vocale a connu un développement rapide récemment',
'ZH': 'text-to-speech 领域近年来发展迅速',
'JP': 'テキスト読み上げの分野は最近急速な発展を遂げています',
'KR': '최근 텍스트 음성 변환 분야가 급속도로 발전하고 있습니다.',
}
def synthesize(speaker, text, speed, language, progress=gr.Progress()):
bio = io.BytesIO()
models[language].tts_to_file(text, models[language].hps.data.spk2id[speaker], bio, speed=speed, pbar=progress.tqdm, format='wav')
return bio.getvalue()
def load_speakers(language, text):
if text in list(default_text_dict.values()):
newtext = default_text_dict[language]
else:
newtext = text
return gr.update(value=list(models[language].hps.data.spk2id.keys())[0], choices=list(models[language].hps.data.spk2id.keys())), newtext
with gr.Blocks() as demo:
gr.Markdown('# MeloTTS Demo\n\nAn unofficial for [MeloTTS](https://github.com/myshell-ai/MeloTTS).')
with gr.Group():
speaker = gr.Dropdown(speaker_ids.keys(), interactive=True, value='EN-US', label='Speaker')
language = gr.Radio(['EN', 'ES', 'FR', 'ZH', 'JP', 'KR'], label='Language', value='EN')
speed = gr.Slider(label='Speed', minimum=0.1, maximum=10.0, value=1.0, interactive=True, step=0.1)
text = gr.Textbox(label="Text to speak", value=default_text_dict['EN'])
language.input(load_speakers, inputs=[language, text], outputs=[speaker, text])
btn = gr.Button('Synthesize', variant='primary')
aud = gr.Audio(interactive=False)
btn.click(synthesize, inputs=[speaker, text, speed, language], outputs=[aud])
gr.Markdown('Demo by [mrfakename](https://twitter.com/realmrfakename).')
demo.queue(api_open=False, default_concurrency_limit=10).launch(show_api=False, share=share, server_name=host, server_port=port)