zhangshuai/MeloTTS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #15 from fakerybakery/patch-1

Browse Source 
Only change text if text is default
This commit is contained in:
Zengyi Qin
2024-02-27 10:22:10 -07:00
committed by GitHub
parent 29f9c65819 72963764d5
commit 72dc688957
1 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
melo/app.py
View File

@@ -27,24 +27,25 @@ default_text_dict = {
'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', '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.', 'KR': '최근 텍스트 음성 변환 분야가 급속도로 발전하고 있습니다.',
} }
def update_default_text_fn(language):
return default_text_dict[language]
def synthesize(speaker, text, speed, language, progress=gr.Progress()): def synthesize(speaker, text, speed, language, progress=gr.Progress()):
bio = io.BytesIO() bio = io.BytesIO()
models[language].tts_to_file(text, models[language].hps.data.spk2id[speaker], bio, speed=speed, pbar=progress.tqdm, format='wav') models[language].tts_to_file(text, models[language].hps.data.spk2id[speaker], bio, speed=speed, pbar=progress.tqdm, format='wav')
return bio.getvalue() return bio.getvalue()
def load_speakers(language): def load_speakers(language, text):
return gr.update(value=list(models[language].hps.data.spk2id.keys())[0], choices=list(models[language].hps.data.spk2id.keys())) 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: with gr.Blocks() as demo:
gr.Markdown('# MeloTTS WebUI\n\nA WebUI for MeloTTS.') gr.Markdown('# MeloTTS WebUI\n\nA WebUI for MeloTTS.')
with gr.Group(): with gr.Group():
speaker = gr.Dropdown(speaker_ids.keys(), interactive=True, value='EN-Default', label='Speaker') speaker = gr.Dropdown(speaker_ids.keys(), interactive=True, value='EN-Default', label='Speaker')
language = gr.Radio(['EN', 'ES', 'FR', 'ZH', 'JP', 'KR'], label='Language', value='EN') language = gr.Radio(['EN', 'ES', 'FR', 'ZH', 'JP', 'KR'], label='Language', value='EN')
language.input(load_speakers, inputs=language, outputs=speaker)
speed = gr.Slider(label='Speed', minimum=0.1, maximum=10.0, value=1.0, interactive=True, step=0.1) 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']) text = gr.Textbox(label="Text to speak", value=default_text_dict['EN'])
language.change(update_default_text_fn, [language], [text]) language.input(load_speakers, inputs=[language, text], outputs=[speaker, text])
btn = gr.Button('Synthesize', variant='primary') btn = gr.Button('Synthesize', variant='primary')
aud = gr.Audio(interactive=False) aud = gr.Audio(interactive=False)
btn.click(synthesize, inputs=[speaker, text, speed, language], outputs=[aud]) btn.click(synthesize, inputs=[speaker, text, speed, language], outputs=[aud])