Hi guys I’m trying to make an own training model, I’m following this guide https://deepspeech.readthedocs.io/en/latest/TRAINING.html#prerequisites-for-training-a-model step by step but when I arrive at this point bin/import_cv2.py --filter_alphabet path/to/some/alphabet.txt /path/to/extracted/language/archive I receive the following errorraceback (most recent call last):
File “bin/import_cv2.py”, line 18, in
from deepspeech_training.util.downloader import SIMPLE_BAR
ModuleNotFoundError: No module named ‘deepspeech_training’
Someone can help me please to fix the problem?
This documentation stipulates you need to perform pip install steps. Since you documented nothing besides the generic link and your error 100% matches the lack of pip install, I would advise at either properly applying the documentation, or properly documenting all the steps you have taken as well as your context so we can help.
Hi thank for your answer, I’ve done the pip installation and using a pre-trained model it works, the problem happen only for a custom model.
Sorry, but this is not helping at all.
Why do you refer to a pre-trained model for ?
This is for inference, you were talking about training.
Again, I insist, we can’t continue with “I followed the docs” since your error obviously shows it is not the case. Please explicit your context, setup and steps to reproduce.
Ok I’ll try all the steps again and I will let you know. I attached the screenshot to show you that pip is installed.
First, no screenshots. Second, read our guidelines. Third read the docs, its not just about pip, you need to perform pip install steps…