Update README.md
Browse files
README.md
CHANGED
@@ -2,9 +2,6 @@
|
|
2 |
MT model trained using the friendly_JA Corpus attempting to make Japanese easier/more accessible to occidental people by using the Latin/English derived katakana lexicon instead of the standard Sino-Japanese lexicon
|
3 |
|
4 |
We used sonoisa t5-base-japanese (https://huggingface.co/sonoisa/t5-base-japanese) as pretrained model and the friendly_JA corpus to fine-tune the friendly_JA model.
|
5 |
-
We provide the pytorch model as well as the onnx quantized model.
|
6 |
-
|
7 |
-
We achieved a 66.80 Bleu Score performed on the pytorch model.
|
8 |
|
9 |
|
10 |
# Examples
|
|
|
2 |
MT model trained using the friendly_JA Corpus attempting to make Japanese easier/more accessible to occidental people by using the Latin/English derived katakana lexicon instead of the standard Sino-Japanese lexicon
|
3 |
|
4 |
We used sonoisa t5-base-japanese (https://huggingface.co/sonoisa/t5-base-japanese) as pretrained model and the friendly_JA corpus to fine-tune the friendly_JA model.
|
|
|
|
|
|
|
5 |
|
6 |
|
7 |
# Examples
|