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

#new imports
import matplotlib.pyplot as plt
import re

from torch import nn
from torch.nn import functional as F
from torch.utils.data import DataLoader

from models import SynthesizerTrn
import unicodedata
import openai

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_1434000.pth", net_g, None) 

def friend_chat(text, tts_input3):
  call_name = "亚托克斯"
  openai.api_key = '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'
  identity = tts_input3
  start_sequence = '\n'+str(call_name)+':'
  restart_sequence = "\nYou: "
  all_text = identity + restart_sequence
  if 1 == 1:
     prompt0 = text #当期prompt
  if text == 'quit':
     return prompt0
  prompt = identity + prompt0 + start_sequence

  response = openai.Completion.create(
    model="text-davinci-003",
    prompt=prompt,
    temperature=0.5,
    max_tokens=1000,
    top_p=1.0,
    frequency_penalty=0.5,
    presence_penalty=0.0,
    stop=["\nYou:"]
  )
  return response['choices'][0]['text'].strip()

def sle(text, tts_input3):
    text = friend_chat(text, tts_input3).replace('\n','。').replace(' ',',')
    return text

def infer(text,tts_input3):
    stn_tst = get_text(sle(text,tts_input3), 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 (sampling_rate, audio)
        
app = gr.Blocks()

with app:
    with gr.Tabs():

        with gr.TabItem("Basic"):

            tts_input1 = gr.TextArea(label="输入你想跟剑魔说的话", value="我是暮光星灵佐伊，我要三天之内杀了你")
            tts_input3 = gr.TextArea(label="写上你给他的设定", value="你叫亚托克斯，俗称剑魔，世界的终结者。")
            tts_submit = gr.Button("Generate", variant="primary")
            tts_output2 = gr.Audio(label="Output")
            tts_submit.click(infer, [tts_input1,tts_input3], [tts_output2])
    app.launch()