Questions tagged [opennmt]

38 questions
1
vote
1 answer

TypeError: __init__() got an unexpected keyword argument 'tensor_type'

I am trying to run a code that was used with older versions of torch and torchtext. I have adjusted a lot in the code to make it work. I was able to pre-process and train my data. Lastly I tried to run the test script, after solving multiple errors,…
U. Iceman
  • 121
  • 1
  • 1
  • 7
1
vote
1 answer

SentencePiece in Google Colab

I want to use sentencepiece, from https://github.com/google/sentencepiece in a Google Colab project where I am training an OpenNMT model. I'm a little confused with how to set up the sentencepiece binaries in Google Colab. Do I need to build with…
1
vote
1 answer

openNMT translate commands yields garbage results

I am running the following command onmt_translate -model demo-model_step_100000.pt -src data/src-test.txt -output pred.txt -replace_unk -verbose The results in the file 'pred.txt' is something completely different than the source sentences given…
girishnjha
  • 81
  • 1
  • 3
1
vote
0 answers

app crash when the execution of model.forward on android code ,i don't know why?

When I execute this code precisely at the line which corresponds to module.forward my apps restarts. Code attached below: @WorkerThread @Nullable public IValue translation(String input){ // loading serialized torchscript module from…
1
vote
1 answer

How to take multi-GPU support to the OpenNMT-py (pytorch)?

I used python-2.7 version to run the PyTorch with GPU support. I used this command to train the dataset using multi-GPU. Can someone please tell me how can I fix this error with PyTorch in OpenNMT-py or is there a way to take pytorch support for…
lnash
  • 53
  • 10
1
vote
2 answers

Getting attention weights in opennmt-py

Specifically in opennmt-py. Now there are many questions on this topic, such as Getting alignment/attention during translation in OpenNMT-py and the following thread on the opennmt forum https://github.com/OpenNMT/OpenNMT-py/issues/575. I use the…
1
vote
0 answers

NeuroX, ValueError: badly formed hexadecimal UUID string

Now this is probably a long shot, but I have a question about a certain flask app called NeuroX, https://github.com/fdalvi/NeuroX. It is a flask app for analyzing neural networks. The details are not that important, but you run the app and enter…
thaumoctopus
  • 113
  • 1
  • 13
1
vote
1 answer

Output hidden state in OpenNMT-py

I just have a short question regarding the pytorch version of OpenNMT. There does not seem to be an option to return the hidden state of encoder and decoder in the options. Am I missing a flag or is this not an option in OpenNMT-py?
thaumoctopus
  • 113
  • 1
  • 13
1
vote
1 answer

OpenNMT issues with Pytorch: cPickle.UnpicklingError: invalid load key, ''

I am trying to run the OpenNMT project using the instruction from the link: http://forum.opennmt.net/t/text-summarization-on-gigaword-and-rouge-scoring/85/6 I am using Python 2.7 and installed pytorch from the github repository. I am trying to run…
Jaffer Wilson
  • 7,029
  • 10
  • 62
  • 139
0
votes
0 answers

what is the Error i am getting while training the NMT Model?

When i Try to train my model with the below code: !onmt-main --model_type Transformer --config train_files/config.yml --auto_config train --with_eval Error Screen Shot then facing this error. TypeError: 'NoneType' object is not…
0
votes
0 answers

how to run translate command in open nmt

I have a folder called sample1 which is residing in OpenNMT-py folder i have completed first 2 steps that is Preparing the data - have created vocabulary Train the data but as i am translating the data with this command You can check the…
Anurag Rao
  • 107
  • 2
0
votes
1 answer

Facing CUDA Error while training MNMT model using fairseq

I was trying to use fairseq to train a model for English-Russian,English-French,English-Spanish,English-German data but have been getting a CUDA Error which prevents me from running the model. I have tried using multiple batch sizes,learning rate…
0
votes
1 answer

How can I use custom tokenizer in opennmt transformer

I'm tring to transformer for translation with opennmt-py. And I already have the tokenizer trained by sentencepiece(unigram). But I don't know how to use my custom tokenizer in training config yaml. I'm refering the site of opennmt-docs…
Shanha_Kim
  • 31
  • 4
0
votes
1 answer

Machine translation transformer output - "unknown" tokens?

When decoding / translating a test dataset after training on the base Transformer model (Vaswani et. al.), I sometimes see this token "unk" in the ouput. "unk" here refers to an unknown token, but my question is what is the reasoning behind that?…
Dametime
  • 581
  • 1
  • 6
  • 23
0
votes
1 answer

ERROR: Could not find a version that satisfies the requirement ctranslate2

I'm learning to use docker and I'm having trouble installing Ctransalte2 inside a docker image. When I run docker build i'm getting the above error. I'm using python:3.8.12 base image which I suspect is the problem. I know Ctranslate2 will only run…
user3447228
  • 478
  • 1
  • 4
  • 12