UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe4 in posotion 47

[c6s0]

Hey,

while trying to use sp-encode [...] sp-model.model [...]/encode im running into this error:
Reading corpora: ['author']
author\train: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:02<00:00, 1.03it/s]
author\valid: 0%| | 0/1 [00:00<?, ?it/s]
Traceback (most recent call last):
File "C:\Users\test\anaconda3\envs\transformertest\Scripts\sp-encode-script.py", line 33, in
sys.exit(load_entry_point('lm', 'console_scripts', 'sp-encode')())
File "c:\users\test\documents\transformer-lm\lm\data.py", line 100, in sp_encode
for line in f:
File "C:\Users\test\anaconda3\envs\transformertest\lib\codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe4 in position 47: invalid continuation byte

I saved all my .txt files with utf-8 codec for the previous step.