search

tensorflow / tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
Apache License 2.0
15.5k stars 3.49k forks source link

How to create new problem for speech recognition #1279

Closed manuel3265 closed 5 years ago

manuel3265 commented 5 years ago

Description

how do I create a new problem to train my own model, but that is for speech recognition, according to how they do it in this link: https://tensorflow.github.io/tensor2tensor/new_problem.html ...

Environment information

OS: <your answer here>

$ pip freeze | grep tensor
# your output here

$ python -V
# your output here

For bugs: reproduction and error logs

# Steps to reproduce:
...
# Error logs:
...
afrozenator commented 5 years ago

Can you take a look here -- https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/data_generators/librispeech.py

Closing this for now, feel free to reopen if that doesn't provide a well enough guide