From 28859ebe96b4b9456ddfe0f61234893fed9d9f9e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Stardust=C2=B7=E5=87=8F?= <2225664821@qq.com> Date: Mon, 21 Aug 2023 08:43:26 +0800 Subject: [PATCH] Update preprocess_text.py --- preprocess_text.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/preprocess_text.py b/preprocess_text.py index 94aea25..0314bba 100644 --- a/preprocess_text.py +++ b/preprocess_text.py @@ -17,8 +17,8 @@ if 1 in stage: with open( transcription_path+'.cleaned', 'w', encoding='utf-8') as f: for line in tqdm.tqdm(open(transcription_path, encoding='utf-8').readlines()): try: - utt, spk, text = line.strip().split('|') - language = "ZH" + utt, spk, language, text = line.strip().split('|') + #language = "ZH" norm_text, phones, tones, word2ph = clean_text(text, language) f.write('{}|{}|{}|{}|{}|{}|{}\n'.format(utt, spk, language, norm_text, ' '.join(phones), " ".join([str(i) for i in tones]),