forked from mozilla/translations
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
added configuration for korean-english
- Loading branch information
Ona De Gibert Bonet
committed
Oct 1, 2024
1 parent
c1e3a2e
commit 8d1686b
Showing
1 changed file
with
39 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,39 @@ | ||
#### | ||
# Example of a production config | ||
# Change language pair, experiment name, datasets and other settings if needed | ||
# Training low resource languages might require more tuning of pipeline/training/configs | ||
### | ||
|
||
experiment: | ||
dirname: hplt | ||
name: kor-eng | ||
langpairs: | ||
- ko-en | ||
|
||
#URL to the OPUS-MT model to use as the teacher | ||
opusmt-teacher: "https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opusTCv20210807-sepvoc_transformer-big_2022-07-28.zip" | ||
|
||
# Specify if the teacher and the student are many2one | ||
one2many-teacher: False | ||
one2many-student: False | ||
|
||
#URL to the OPUS-MT model to use as the backward model | ||
opusmt-backward: "" | ||
|
||
teacher-ensemble: 1 | ||
|
||
split-length: 20000000 | ||
spm-sample-size: 2000000 | ||
|
||
best-model: perplexity | ||
|
||
opusfilter: | ||
config: default | ||
|
||
datasets: | ||
train: | ||
- tc_Tatoeba-Challenge-v2023-09-26 | ||
devtest: | ||
- flores_dev | ||
test: | ||
- flores_devtest |