Issues
- 6
Setting seq-to-seq model as our pretrained model
#49 opened by b3ade - 1
- 2
Training details
#57 opened by CBHhD - 1
Torch.save() for large training Dataset
#56 opened by stelmath - 1
A bug(maybe)
#55 opened by shaoyangxu - 1
- 4
- 1
- 2
Question on Figure 2 in your paper
#51 opened by gpengzhi - 3
Extracting dataset and AttributeError
#44 opened by b3ade - 2
Alignment prob matrix visualization tool?
#50 opened by kirklandWater1 - 1
- 1
Trying to train on an existing model
#47 opened - 1
Statistics between models
#46 opened by b3ade - 3
traning is increasing my aer
#36 opened by vigneshmj1997 - 2
- 3
How to test fine tuned model on parallel data?
#40 opened by MusfiqDehan - 1
How can I resume training from a checkpoint?
#42 opened by MusfiqDehan - 3
Abort experiment in Table 8
#45 opened by sdongchuanqi - 2
How to get test results?
#43 opened by QzzIsCoding - 2
Continue with checkpoint
#39 opened by kirklandWater1 - 1
- 2
- 1
Can I evaluate separately?
#34 opened by ruoyuxie - 5
Wrong mapping with non-matching sentences
#9 opened by mzeidhassan - 3
problem with mask_token
#32 opened by v-zixin - 2
Training with gold alignment
#31 opened by ruoyuxie - 1
- 2
Fasten the extraction process
#30 opened by shanyas10 - 4
- 1
De-En dataset is missing
#27 opened by ruoyuxie - 2
setting output prob file and output word file
#26 opened by pskadasi - 5
Can I use the XML-R model?
#23 opened by sadanyh - 2
- 4
- 2
Not able to reproduce the AERs in the table
#20 opened by jinyiyang-jhu - 2
- 8
some confusions
#17 opened by leileilin - 2
- 6
Reproduction of Ja-En
#14 opened by twadada - 5
No caching
#11 opened by BramVanroy - 0
Multiple GPUs
#10 opened by BramVanroy - 4
pip packaging?
#8 opened by neubig - 4
- 10
Index out of range
#3 opened by mapmeld - 2
Error reading fine-tuned models
#2 opened by dmitrytoda - 1
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte
#1 opened by echan00