From 34920cacecaf3c78a05919a4a840fb4645c72569 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=BC=A0=E6=98=A5=E4=B9=94?= <83450930+Liyulingyue@users.noreply.github.com> Date: Sun, 1 Dec 2024 05:23:13 +0800 Subject: [PATCH] Apply suggestions from code review --- paddlespeech/t2s/exps/fastspeech2/preprocess.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/paddlespeech/t2s/exps/fastspeech2/preprocess.py b/paddlespeech/t2s/exps/fastspeech2/preprocess.py index dd3da6c2e..a2353242b 100644 --- a/paddlespeech/t2s/exps/fastspeech2/preprocess.py +++ b/paddlespeech/t2s/exps/fastspeech2/preprocess.py @@ -271,9 +271,9 @@ def main(): if args.dataset == "baker": wav_files = sorted(list((rootdir / "Wave").rglob("*.wav"))) - # split data into 3 sections, the max number of dev/test is 10% or 100 - num_dev = min(int(len(wav_files) * 0.1), 100) - num_train = len(wav_files) - num_dev * 2 + # split data into 3 sections + num_train = 9800 + num_dev = 100 train_wav_files = wav_files[:num_train] dev_wav_files = wav_files[num_train:num_train + num_dev] test_wav_files = wav_files[num_train + num_dev:]