mrq/DL-Art-School
1
3
Fork 5
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added japanese preprocessor for tokenizer

Browse Source
This commit is contained in:
mrq 2023-03-17 20:03:57 +00:00
parent 7b5e0592f8
commit 64a41fde24
1 changed files with 17 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
codes/data/audio/voice_tokenizer.py
View File

@ -32,17 +32,30 @@ def remove_extraneous_punctuation(word):
class VoiceBpeTokenizer:
def __init__(self, vocab_file, preprocess=None):
with open(vocab_file, 'r', encoding='utf-8') as f:
vocab = json.load(f)
self.language = vocab['model']['language'] if 'language' in vocab['model'] else None
if preprocess is None:
with open(vocab_file, 'r', encoding='utf-8') as f:
vocab = json.load(f)
self.preprocess = 'pre_tokenizer' in vocab and vocab['pre_tokenizer']
self.preprocess = 'pre_tokenizer' in vocab and vocab['pre_tokenizer']
else:
self.preprocess = preprocess
if vocab_file is not None:
self.tokenizer = Tokenizer.from_file(vocab_file)
def preprocess_text(self, txt):
txt = english_cleaners(txt)
if self.language == 'ja':
import pykakasi
kks = pykakasi.kakasi()
results = kks.convert(txt)
txt = " ".join([ result['kana'] for result in results ])
txt = basic_cleaners(txt)
else:
txt = english_cleaners(txt)
return txt
def encode(self, txt):