I have a problem when i train my own model

[JRMeyer]

>>> rjzevallos.salazar
[February 17, 2020, 4:38am]

When I run:

python3 train.py --config_path config.json

I get this:

Traceback (most recent call last):
File 'train.py', line 13, in
from TTS.datasets.TTSDataset import MyDataset
File '/home/begemot/Escritorio/TTS-master/tts_namespace/TTS/datasets /TTSDataset.py', line 8, in
from TTS.utils.text import text_to_sequence, phoneme_to_sequence, pad_with_eos_bos
File '/home/begemot/Escritorio/TTS-master/tts_namespace/TTS/utils/text/init.py', line 5, in
from phonemizer.phonemize import phonemize
File '', line 969, in _find_and_load
File '', line 958, in _find_and_load_unlocked
File '', line 664, in _load_unlocked
File '', line 634, in _load_backward_compatible
File '/usr/local/lib/python3.5/dist-packages/phonemizer-2.1-py3.5.egg/phonemizer/phonemize.py', line 25, in
File '', line 969, in _find_and_load
File '', line 954, in _find_and_load_unlocked
File '', line 896, in _find_spec
File '', line 1139, in find_spec
File '', line 1115, in _get_spec
File '', line 1096, in _legacy_get_spec
File '', line 444, in spec_from_loader
File '', line 533, in spec_from_file_location
File '/usr/local/lib/python3.5/dist-packages/phonemizer-2.1-py3.5.egg/phonemizer/logger.py', line 42
f'verbosity is {verbosity} but must be in '
^
SyntaxError: invalid syntax

[This is an archived TTS discussion thread from discourse.mozilla.org/t/i-have-a-problem-when-i-train-my-own-model]

[JRMeyer]

>>> sanjaesc
[February 17, 2020, 9:07am]

for easier installation.

You need atleast python 3.6

[Archived Post]

[JRMeyer]

>>> kurian.bkk
[February 18, 2020, 8:12am]

[ slash sanjasec] why are you emphasising on using miniconda?
What's the issue with pip?

[Archived Post]

[JRMeyer]

>>> sanjaesc
[February 18, 2020, 9:02am]

I just copied the requirements from
https://github.com/mozilla/TTS#requirements-and-installation

pip should work just fine.


[Archived Post]