Update train.py

train.py

@@ -3,8 +3,6 @@ import multiprocessing
 import time
 
 logging.getLogger('matplotlib').setLevel(logging.WARNING)
-logging.getLogger('numba').setLevel(logging.WARNING)
-
 import os
 import json
 import argparse
@@ -67,15 +65,12 @@ def run(rank, n_gpus, hps):
     torch.manual_seed(hps.train.seed)
     torch.cuda.set_device(rank)
     collate_fn = TextAudioCollate()
-    all_in_mem = hps.train.all_in_mem   # If you have enough memory, turn on this option to avoid disk IO and speed up training.
-    train_dataset = TextAudioSpeakerLoader(hps.data.training_files, hps, all_in_mem=all_in_mem)
+    train_dataset = TextAudioSpeakerLoader(hps.data.training_files, hps)
     num_workers = 5 if multiprocessing.cpu_count() > 4 else multiprocessing.cpu_count()
-    if all_in_mem:
-        num_workers = 0
     train_loader = DataLoader(train_dataset, num_workers=num_workers, shuffle=False, pin_memory=True,
                               batch_size=hps.train.batch_size, collate_fn=collate_fn)
     if rank == 0:
-        eval_dataset = TextAudioSpeakerLoader(hps.data.validation_files, hps, all_in_mem=all_in_mem)
+        eval_dataset = TextAudioSpeakerLoader(hps.data.validation_files, hps)
         eval_loader = DataLoader(eval_dataset, num_workers=1, shuffle=False,
                                  batch_size=1, pin_memory=False,
                                  drop_last=False, collate_fn=collate_fn)