Hugging Face's logo

Addy1008
/
adarsh-mBART-codemixed

Transformers
PyTorch
mbart
text2text-generation
Model card Files
xet
 Community
1
Addy1008 commited on
Commit
540b8ae
·
verified ·
1 Parent(s): dce7f81

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -1,3 +1,3 @@
1
  mBART (a pre-trained model by Facebook) is pre-trained to de-noise multiple languages simultaneously with BART objective.
2
 
3
- Checkpoint available in this repository is obtained after fine-tuning facebook/mbart-large-cc25 on 14000 samples from IIT-B Hindi-English parallel corpus. This checkpoint gives decent results for Hindi-english translation.
 
1
  mBART (a pre-trained model by Facebook) is pre-trained to de-noise multiple languages simultaneously with BART objective.
2
 
3
+ Checkpoint available in this repository is obtained after fine-tuning facebook/mbart-large-cc25 on 10000 samples from manually generated corpus. This checkpoint gives decent results for Hindi-english translation.