Apply suggestions from code review

paddlespeech/t2s/exps/ernie_sat/preprocess.py

@@ -241,9 +241,9 @@ 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:]

paddlespeech/t2s/exps/fastspeech2/gen_gta_mel.py

@@ -81,9 +81,9 @@ def evaluate(args, fastspeech2_config):
 
     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:]