Merge pull request #3 from candlewill/patch-1

specify encoding method

datasets/ljspeech.py

@@ -9,7 +9,7 @@ def build_from_path(in_dir, out_dir, num_workers=1, tqdm=lambda x: x):
   executor = ProcessPoolExecutor(max_workers=num_workers)
   futures = []
   index = 1
-  with open(os.path.join(in_dir, 'metadata.csv')) as f:
+  with open(os.path.join(in_dir, 'metadata.csv'), encoding="utf-8") as f:
     for line in f:
       parts = line.strip().split('|')
       wav_path = os.path.join(in_dir, 'wavs', '%s.wav' % parts[0])