riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 33 Packages Projects Releases Wiki Activity

dv-wave (#5823)

Browse Source
This commit is contained in:
Nick Doiron 2020-07-16 15:13:51 -04:00 committed by GitHub
parent 283500ff9f
commit 233072fc1e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 28 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
model_cards/monsoon-nlp/dv-wave/README.md Normal file
View File

@ -0,0 +1,28 @@
---
language: dv
---
# dv-wave
This is a second attempt at a Dhivehi language model trained with
Google Research's [ELECTRA](https://github.com/google-research/electra).
Tokenization and pre-training CoLab: https://colab.research.google.com/drive/1ZJ3tU9MwyWj6UtQ-8G7QJKTn-hG1uQ9v?usp=sharing
Using SimpleTransformers to classify news https://colab.research.google.com/drive/1KnyQxRNWG_yVwms_x9MUAqFQVeMecTV7?usp=sharing
V1: similar performance to mBERT on news classification task after finetuning for 3 epochs (52%)
V2: fixed tokenizers ```do_lower_case=False``` and ```strip_accents=False``` to preserve vowel signs of Dhivehi
dv-wave: 89% to mBERT: 52%
## Corpus
Trained on @Sofwath's 307MB corpus of Dhivehi text: https://github.com/Sofwath/DhivehiDatasets - this repo also contains the news classification task CSV
[OSCAR](https://oscar-corpus.com/) was considered but has not been added to pretraining; as of
this writing their web crawl has 126MB of Dhivehi text (79MB deduped).
## Vocabulary
Included as vocab.txt in the upload - vocab_size is 29874