A PyTorch implementation of a punctuation prediction system using (B)LSTM, which automatically adds suitable punctuation into text without punctuation.
A PyTorch implementation of punctuation prediction system using LSTM/BLSTM [1][2][3], which automatically adds suitable punctation into text without punctuation.
egs/toy/run.sh
provides an example usage.
# Set PATH and PYTHONPATH
$ cd egs/toy/; . ./path.sh
# Train
$ train.py -h
# Add punctuation
$ add_punctuation.py -h
# Analyze metrics
$ analyer.py -h
If you want to visualize your loss, you can use visdom to do that:
$ visdom
.$ train.py ... --visdom 1 --vidsdom_id "<any-string>"
.<your-remote-server-ip>:8097
, egs, 127.0.0.1:8097
.<any-string>
in Environment
to see your loss.$ train.py --continue_from <model-path>
Use comma separated gpu-id sequence, such as:
$ CUDA_VISIBLE_DEVICES="0,1" train.py