synthesize.py

import re
import argparse
from string import punctuation

import torch
import yaml
import numpy as np
from torch.utils.data import DataLoader
from g2p_en import G2p
from pypinyin import pinyin, Style

from utils.model import get_model, get_vocoder
from utils.tools import to_device, synth_samples
from dataset import TextDataset
from text import text_to_sequence

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")


def read_lexicon(lex_path):
    lexicon = {}
    with open(lex_path) as f:
        for line in f:
            temp = re.split(r"\s+", line.strip("\n"))
            word = temp[0]
            phones = temp[1:]
            if word.lower() not in lexicon:
                lexicon[word.lower()] = phones
    return lexicon


def preprocess_english(text, preprocess_config):
    text = text.rstrip(punctuation)
    lexicon = read_lexicon(preprocess_config["path"]["lexicon_path"])

    g2p = G2p()
    phones = []
    words = re.split(r"([,;.\-\?\!\s+])", text)
    for w in words:
        if w.lower() in lexicon:
            phones += lexicon[w.lower()]
        else:
            phones += list(filter(lambda p: p != " ", g2p(w)))
    phones = "{" + "}{".join(phones) + "}"
    phones = re.sub(r"\{[^\w\s]?\}", "{sp}", phones)
    phones = phones.replace("}{", " ")

    print("Raw Text Sequence: {}".format(text))
    print("Phoneme Sequence: {}".format(phones))
    sequence = np.array(
        text_to_sequence(
            phones, preprocess_config["preprocessing"]["text"]["text_cleaners"]
        )
    )

    return np.array(sequence)


def synthesize(model, step, configs, vocoder, batchs):
    preprocess_config, model_config, train_config = configs

    for batch in batchs:
        batch = to_device(batch, device)
        with torch.no_grad():
            # Forward
            output = model(
                *(batch[2:])
            )
            synth_samples(
                batch,
                output,
                vocoder,
                model_config,
                preprocess_config,
                train_config["path"]["result_path"],
            )


if __name__ == "__main__":

    parser = argparse.ArgumentParser()
    parser.add_argument("--restore_step", type=int, required=True)
    parser.add_argument(
        "--text",
        type=str,
        default=None,
        help="raw text to synthesize, for single-sentence mode only",
    )
    parser.add_argument(
        "-p",
        "--preprocess_config",
        type=str,
        required=True,
        help="path to preprocess.yaml",
    )
    parser.add_argument(
        "-m", "--model_config", type=str, required=True, help="path to model.yaml"
    )
    parser.add_argument(
        "-t", "--train_config", type=str, required=True, help="path to train.yaml"
    )
    args = parser.parse_args()

    # Check source texts
    assert args.text is not None

    # Read Config
    preprocess_config = yaml.load(
        open(args.preprocess_config, "r"), Loader=yaml.FullLoader
    )
    model_config = yaml.load(open(args.model_config, "r"), Loader=yaml.FullLoader)
    train_config = yaml.load(open(args.train_config, "r"), Loader=yaml.FullLoader)
    configs = (preprocess_config, model_config, train_config)

    # Get model
    model = get_model(args, configs, device, train=False)

    # Load vocoder
    vocoder = get_vocoder(model_config, device)

    ids = raw_texts = [args.text[:100]]
    speakers = np.array([args.speaker_id])
    if preprocess_config["preprocessing"]["text"]["language"] == "en":
        texts = np.array([preprocess_english(args.text, preprocess_config)])
    text_lens = np.array([len(texts[0])])
    batchs = [(ids, raw_texts, speakers, texts, text_lens, max(text_lens))]

    synthesize(model, args.restore_step, configs , vocoder, batchs)