app.py

import gradio as gr
import os
os.system('cd monotonic_align && python setup.py build_ext --inplace && cd ..')
import torch

import commons
import utils
from models import SynthesizerTrn
from text.symbols import symbols
from text import text_to_sequence

import IPython.display as ipd

import json
import math

def get_text(text, hps):
    text_norm = text_to_sequence(text, hps.data.text_cleaners)
    if hps.data.add_blank:
        text_norm = commons.intersperse(text_norm, 0)
    text_norm = torch.LongTensor(text_norm)
    return text_norm

hps = utils.get_hparams_from_file("configs/biaobei_base.json")

net_g = SynthesizerTrn(
    len(symbols),
    hps.data.filter_length // 2 + 1,
    hps.train.segment_size // hps.data.hop_length,
    **hps.model)
_ = net_g.eval()

_ = utils.load_checkpoint("G_aatrox.pth", net_g, None) 
import soundfile as sf
text = "\u6211\u662F\u4E9A\u6258\u514B\u65AF\uFF0C\u4E16\u754C\u7684\u7EC8\u7ED3\u8005\uFF01" #@param {type: 'string'}
length_scale = 1 #@param {type:"slider", min:0.1, max:3, step:0.05}
filename = 'test' #@param {type: "string"}
audio_path = f'/content/VITS-Aatrox/{filename}.wav'
stn_tst = get_text(text, hps)
with torch.no_grad():
    x_tst = stn_tst.unsqueeze(0)
    x_tst_lengths = torch.LongTensor([stn_tst.size(0)])
    audio = net_g.infer(x_tst, x_tst_lengths, noise_scale=.667, noise_scale_w=0.8, length_scale=length_scale)[0][0,0].data.cpu().float().numpy()
ipd.display(ipd.Audio(audio, rate=hps.data.sampling_rate))


# def vc_fn(input):
#     stn_tst = get_text(input, hps)
#     with torch.no_grad():
#         x_tst = stn_tst.unsqueeze(0)
#         x_tst_lengths = torch.LongTensor([stn_tst.size(0)])
#         audio = net_g.infer(x_tst, x_tst_lengths, noise_scale=.667, noise_scale_w=0.8, length_scale=1)[0][0,0].data.cpu().float().numpy()
#     sampling_rate = 22050
#     return (audio, sampling_rate)
        # 
# app = gr.Blocks()
# with app:
#     with gr.Tabs():
#         with gr.TabItem("Basic"):
#             vc_input = gr.Textbox(label="Input Message")
#             vc_submit = gr.Button("Convert", variant="primary")
#             vc_output = gr.Audio(label="Output Audio")
#             #vc_output = ipd.display(ipd.Audio(vc_fn(get_text(vc_input, hps)), rate=hps.data.sampling_rate))
#         vc_submit.click(vc_fn, [vc_input], [vc_output])

#     app.launch()