Mitsua commited on
Commit
8c76c40
1 Parent(s): 9e38a35

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +38 -3
README.md CHANGED
@@ -1,3 +1,38 @@
1
- ---
2
- license: cc-by-sa-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-sa-4.0
3
+ datasets:
4
+ - Mitsua/wikidata-parallel-descriptions-en-ja
5
+ language:
6
+ - ja
7
+ - en
8
+ metrics:
9
+ - bleu
10
+ - chrf
11
+ library_name: transformers
12
+ pipeline_tag: translation
13
+ ---
14
+ # ElanMT
15
+ This model is a tiny variant of [**ElanMT-BT-ja-en**](https://huggingface.co/Mitsua/elan-mt-bt-ja-en) and is trained from scratch exclusively on openly licensed data and Wikipedia back translated data using [**ElanMT-base-en-ja**](https://huggingface.co/Mitsua/elan-mt-base-en-ja).
16
+
17
+ ## Model Details
18
+ This is a translation model based on [Marian MT](https://marian-nmt.github.io/) 4-layer encoder-decoder transformer architecture with sentencepiece tokenizer.
19
+ - **Developed by**: [ELAN MITSUA Project](https://elanmitsua.com/en/) / Abstract Engine
20
+ - **Model type**: Translation
21
+ - **Source Language**: Japanese
22
+ - **Target Language**: English
23
+ - **License**: [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/)
24
+
25
+ ## Usage
26
+ [See here.](https://huggingface.co/Mitsua/elan-mt-bt-ja-en#usage)
27
+
28
+ ## Training Data
29
+ [See here.](https://huggingface.co/Mitsua/elan-mt-bt-ja-en#training-data)
30
+
31
+ ## Training Procedure
32
+ [See here.](https://huggingface.co/Mitsua/elan-mt-bt-ja-en#training-procedure)
33
+
34
+ ## Evaluation
35
+ [See here.](https://huggingface.co/Mitsua/elan-mt-bt-ja-en#evaluation)
36
+
37
+ ## Disclaimer
38
+ The translated result may be very incorrect, harmful or biased. The model was developed to investigate achievable performance with only a relatively small, licensed corpus, and is not suitable for use cases requiring high translation accuracy. Under Section 5 of the CC BY-SA 4.0 License, ELAN MITSUA Project / Abstract Engine is not responsible for any direct or indirect loss caused by the use of the model.