Update README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Bangla-Electra
|
| 2 |
+
|
| 3 |
+
This is a first attempt at a Bangla/Bengali language model trained with
|
| 4 |
+
Google Research's [ELECTRA](https://github.com/google-research/electra).
|
| 5 |
+
|
| 6 |
+
Tokenization and pre-training CoLab: https://colab.research.google.com/drive/1gpwHvXAnNQaqcu-YNx1kafEVxz07g2jL
|
| 7 |
+
|
| 8 |
+
## Corpus
|
| 9 |
+
|
| 10 |
+
Trained on a web crawl from https://oscar-corpus.com/ (deduped version, 5.8GB) and 1 July 2020 dump of bn.wikipedia.org (414MB)
|
| 11 |
+
|
| 12 |
+
## Vocabulary
|
| 13 |
+
|
| 14 |
+
Included as vocab.txt in the upload - vocab_size is 29898
|