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

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/config.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("logs/woman_csmsc/G_100000.pth", net_g, None) 
_ = utils.load_checkpoint("G_98000.pth", net_g, None) 

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)])

        # x_tst = stn_tst.cpu().unsqueeze(0)
        # x_tst_lengths = torch.LongTensor([stn_tst.size(0)]).cpu()

        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 = 44100
    return (sampling_rate, audio)
        
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_submit.click(vc_fn, [ vc_input], [vc_output])

    app.launch()