From 2ca74b8ab3e78b92e4f0d319f5e8b211a2ad121e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eren=20G=C3=B6lge?= Date: Wed, 17 Feb 2021 13:35:23 +0000 Subject: [PATCH] add RUSLAN dataset preprocessor --- TTS/tts/datasets/preprocess.py | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/TTS/tts/datasets/preprocess.py b/TTS/tts/datasets/preprocess.py index 7815d87d..bed76c86 100644 --- a/TTS/tts/datasets/preprocess.py +++ b/TTS/tts/datasets/preprocess.py @@ -153,7 +153,8 @@ def mailabs(root_path, meta_files=None): def ljspeech(root_path, meta_file): - """Normalizes the Nancy meta data file to TTS format""" + """Normalizes the LJSpeech meta data file to TTS format + https://keithito.com/LJ-Speech-Dataset/""" txt_file = os.path.join(root_path, meta_file) items = [] speaker_name = "ljspeech" @@ -166,6 +167,21 @@ def ljspeech(root_path, meta_file): return items +def ruslan(root_path, meta_file): + """Normalizes the RUSLAN meta data file to TTS format + https://ruslan-corpus.github.io/""" + txt_file = os.path.join(root_path, meta_file) + items = [] + speaker_name = "ljspeech" + with open(txt_file, 'r') as ttf: + for line in ttf: + cols = line.split('|') + wav_file = os.path.join(root_path, 'RUSLAN', cols[0] + '.wav') + text = cols[1] + items.append([text, wav_file, speaker_name]) + return items + + def css10(root_path, meta_file): """Normalizes the CSS10 dataset file to TTS format""" txt_file = os.path.join(root_path, meta_file)