Skip to content
This repository was archived by the owner on Oct 31, 2023. It is now read-only.
This repository was archived by the owner on Oct 31, 2023. It is now read-only.

How to train the model without para_dataset #97

Description

@huyphan168

I am training UNMT using monolingual only however due to the lack of parallel data between languages, i dont have para_dataset paths for the command. Here is my error:
Traceback (most recent call last):
File "/content/UnsupervisedMT/NMT/main.py", line 356, in
main(params)
File "/content/UnsupervisedMT/NMT/main.py", line 241, in main
data = load_data(params)
File "/content/UnsupervisedMT/NMT/src/data/loader.py", line 496, in load_data
load_para_data(params, data)
File "/content/UnsupervisedMT/NMT/src/data/loader.py", line 147, in load_para_data
assert len(params.para_dataset) > 0
AssertionError
@glample can you help me, thank you.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions