Spaces:
Runtime error
Runtime error
File size: 2,393 Bytes
55f7374 5a030e1 b982160 daec3ad 5a030e1 21f8765 daec3ad 55f7374 daec3ad 215fe46 bb9a8ee 215fe46 b811c33 fe151c1 c9e0fc1 215fe46 daec3ad 5950a5c bb9a8ee |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
import gradio as gr
import edge_tts
import asyncio
import librosa
import soundfile
import io
import argparse
import numpy as np
from inference.infer_tool import Svc
def get_or_create_eventloop():
try:
return asyncio.get_event_loop()
except RuntimeError as ex:
if "There is no current event loop in thread" in str(ex):
loop = asyncio.new_event_loop()
asyncio.set_event_loop(loop)
return asyncio.get_event_loop()
def tts_get_voices_list():
voices = []
tts_voice_list = asyncio.get_event_loop().run_until_complete(edge_tts.list_voices())
for item in tts_voice_list:
voices.append(item['ShortName'])
return voices
def infer(txt, input_audio, voice, audio_mode):
tts = asyncio.run(edge_tts.Communicate(txt, voice).save('audio.mp3'))
audio, sr = librosa.load('audio.mp3', sr=16000, mono=True)
raw_path = io.BytesIO()
soundfile.write(raw_path, audio, 16000, format="wav")
raw_path.seek(0)
model = Svc(fr"Herta-Svc/G_10000.pth", f"Herta-Svc/config.json", device = 'cpu')
out_audio, out_sr = model.infer('speaker0', 0, raw_path, auto_predict_f0 = True,)
return (44100, out_audio.cpu().numpy())
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--device', type=str, default='cpu')
parser.add_argument('--api', action="store_true", default=False)
parser.add_argument("--share", action="store_true", default=False, help="share gradio app")
args = parser.parse_args()
loop = asyncio.new_event_loop()
asyncio.set_event_loop(loop)
with gr.Blocks() as app:
with gr.Tabs():
with gr.TabItem('Herta'):
title = gr.Label('Herta Sovits Model')
cover = gr.Markdown('<div align="center">'
f'<img style="width:auto;height:300px;" src="file/Herta-Svc/herta.png">'
'</div>')
tts_text = gr.Textbox(label="TTS text (100 words limitation)", visible = True)
tts_voice = gr.Dropdown(choices= tts_get_voices_list(), visible = True)
audio_output = gr.Audio(label="Output Audio")
btn_submit = gr.Button("Generate")
btn_submit.click(infer, [tts_text, tts_voice], [audio_output])
app.queue(concurrency_count=1, api_open=args.api).launch(share=args.share) |