| # -*- coding: utf-8 -*- | |
| from transformers import AutoTokenizer, AutoModel | |
| tokenizer = AutoTokenizer.from_pretrained("SECode/Gradio/t5-base") | |
| model = AutoModel.from_pretrained("SECode/Gradio/t5-base") | |
| text = "In terms of time." | |
| # Tokenize the text | |
| batch = tokenizer.prepare_seq2seq_batch(src_texts=[text]) | |
| # Make sure that the tokenized text does not exceed the maximum | |
| # allowed size of 512 | |
| batch["input_ids"] = batch["input_ids"][:, :512] | |
| batch["attention_mask"] = batch["attention_mask"][:, :512] | |
| # Perform the translation and decode the output | |
| translation = model.generate(**batch) | |
| result = tokenizer.batch_decode(translation, skip_special_tokens=True) | |
| print(result) | |