4edcfb3fef
* Create all_process.py * Create asr_transcript.py * Update config.py * Create extract_list.py * Create clean_list.py * Create custom.css * Create compress_model.py * Update all_process.py * Update resample.py * Update resample.py * configs/config.json copy utils * mirror: openi + token bert models optimize * text/__init__.py platform compatibility compress_model.py output * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
62 lines
1.8 KiB
Python
62 lines
1.8 KiB
Python
from text.symbols import *
|
|
|
|
_symbol_to_id = {s: i for i, s in enumerate(symbols)}
|
|
|
|
|
|
def cleaned_text_to_sequence(cleaned_text, tones, language):
|
|
"""Converts a string of text to a sequence of IDs corresponding to the symbols in the text.
|
|
Args:
|
|
text: string to convert to a sequence
|
|
Returns:
|
|
List of integers corresponding to the symbols in the text
|
|
"""
|
|
phones = [_symbol_to_id[symbol] for symbol in cleaned_text]
|
|
tone_start = language_tone_start_map[language]
|
|
tones = [i + tone_start for i in tones]
|
|
lang_id = language_id_map[language]
|
|
lang_ids = [lang_id for i in phones]
|
|
return phones, tones, lang_ids
|
|
|
|
|
|
def get_bert(norm_text, word2ph, language, device):
|
|
from .chinese_bert import get_bert_feature as zh_bert
|
|
from .english_bert_mock import get_bert_feature as en_bert
|
|
from .japanese_bert import get_bert_feature as jp_bert
|
|
|
|
lang_bert_func_map = {"ZH": zh_bert, "EN": en_bert, "JP": jp_bert}
|
|
bert = lang_bert_func_map[language](norm_text, word2ph, device)
|
|
return bert
|
|
|
|
|
|
def check_bert_models():
|
|
import json
|
|
from pathlib import Path
|
|
|
|
from config import config
|
|
from .bert_utils import _check_bert
|
|
|
|
if config.mirror.lower() == "openi":
|
|
import openi
|
|
|
|
kwargs = {"token": config.openi_token} if config.openi_token else {}
|
|
openi.login(**kwargs)
|
|
|
|
with open("./bert/bert_models.json", "r") as fp:
|
|
models = json.load(fp)
|
|
for k, v in models.items():
|
|
local_path = Path("./bert").joinpath(k)
|
|
_check_bert(v["repo_id"], v["files"], local_path)
|
|
|
|
|
|
def init_openjtalk():
|
|
import platform
|
|
|
|
if platform.platform() == "Linux":
|
|
import pyopenjtalk
|
|
|
|
pyopenjtalk.g2p("こんにちは，世界。")
|
|
|
|
|
|
init_openjtalk()
|
|
check_bert_models()
|