seq2seq
Here are 773 public repositories matching this topic...
-
Updated
May 26, 2021 - HTML
-
Updated
Oct 9, 2019 - Python
-
Updated
Nov 2, 2020 - Jupyter Notebook
-
Updated
Mar 2, 2021 - Jupyter Notebook
-
Updated
Mar 12, 2021 - Jupyter Notebook
-
Updated
Jul 21, 2019 - Python
-
Updated
Jun 21, 2021 - Python
-
Updated
Jun 21, 2021 - Scala
-
Updated
May 5, 2021 - Python
-
Updated
Mar 23, 2019 - Python
-
Updated
Jun 21, 2021
-
Updated
Feb 10, 2020 - Python
-
Updated
Oct 15, 2018 - Jupyter Notebook
-
Updated
Apr 16, 2021 - Python
-
Updated
May 11, 2021 - Python
-
Updated
May 25, 2020 - Python
预训练模型下载地址修改
建议在readme里面添加预训练模型环境变量地址修改的提示。
我之前遇到过磁盘空间不够,原因就是这个问题
但不是所有人都会debug源码去查看框架读的是哪个系统变量
-
Updated
Dec 26, 2019 - Python
-
Updated
Jun 17, 2021 - Python
The code would already produce charts in English. However, the current charts are in French.
One would need to try all the exercises to regenerate new charts, incorporate them in the notebook, and then regenerate the README in a clean way, as well as the .py file if the code in the notebook changed.
The French branch (which is named francais) should remain untouched.
-
Updated
Feb 23, 2021 - Python
-
Updated
Dec 3, 2020 - Python
-
Updated
May 6, 2021 - Lua
-
Updated
Jun 19, 2017 - Python
-
Updated
Dec 13, 2020 - Python
-
Updated
Jan 12, 2018 - Jupyter Notebook
-
Updated
Nov 19, 2018 - Python
-
Updated
Nov 12, 2019 - Python
-
Updated
Jun 5, 2021 - Python
Improve this page
Add a description, image, and links to the seq2seq topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the seq2seq topic, visit your repo's landing page and select "manage topics."
Add better error message to
HubertForCTC,Wav2Vec2ForCTCif labels are bigger than vocab size.Motivation
Following this issue: huggingface/transformers#12264 it is clear that an error message should be thrown if any of the any of the labels are >
self.config.vocab_sizeor else silent errors can sneak into the training script.So w