SEBIS/code_trans_t5_small_source_code_summarization_csharp

The CodeTrans model is based on the t5-small model architecture . It has its own SentencePiece vocabulary model . It can be used on unparsed and untokenized csharp code . The model could be used to generate the description for the csharp function or be fine-tuned on other csharp codes . It works best with tokenized code functions, but the performance should be better if the code is tokenized . The supervised training tasks datasets can be downloaded on Link.Evaluation results are based on different programming languages (in BLEU score): test results :.python, python, python and python.Python.C#C#Python.Python,