Update README.md

README.md

@@ -8,28 +8,30 @@ metrics:
 pipeline_tag: translation
 ---
 
-# Model Card for Model ID
+# Model Card for Japanese-English Academic Translator [sentence]
 
-<!-- This model is finetuned to translate academic text from Japanese to English -->
+[This model is fine-tuned from MarianMT to translate academic text from Japanese to English.]
 
 
 
 ## Model Details
 
 ### Model Description
-- **Developed by:** Kenneth Zhang and Susie Xu
-- **Language(s) (NLP):** [Japanese to English]
-- **Finetuned from model [MarianMT]
+- **Developed by:** [Kenneth Zhang and Susie Xu]
+- **Languages:** [Japanese to English]
+- **Finetuned from model:** [MarianMT]
 
 
 ## Uses
 
-This model is for translating academic text from Japanese to English.
+[This model is for translating academic text from Japanese to English.
 You can use it through HuggingFace's pipeline by importing it to your environment.
 Otherwise, you can use our interface on HuggingFace Spaces at https://huggingface.co/spaces/ywc1/ja-en-trans.
 This model is finetuned on sentence-level pairs and does not perform very well for multi-sentence inputs.
-If you're looking to translate an entire abstract or paragraph level data, please go to our paragraph level translation model trained from the same datset.
-you can find it at ywc1/mbart-finetuned-ja-en-para
+If you're looking to translate an entire abstract or paragraph-level data, please go to our paragraph level translation model trained from the same datset.
+you can find it at ywc1/mbart-finetuned-ja-en-para.]
+
+Example code:
 
 ```python
 from transformers import MarianMTModel, MarianTokenizer
@@ -43,10 +45,8 @@ tokenizer = MarianTokenizer.from_pretrained("ywc1/marian-finetuned-ja-en")
 ## Training Details
 
 ### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
+[This model finetunes MarianMT on 300,000 pairs of Japanese-English academic text.
+Marian MT i s]
 
 ### Training Procedure