Instructions to use Aminrhmni/PersianAutomaticPunctuation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Aminrhmni/PersianAutomaticPunctuation with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Aminrhmni/PersianAutomaticPunctuation") model = AutoModelForSeq2SeqLM.from_pretrained("Aminrhmni/PersianAutomaticPunctuation") - Notebooks
- Google Colab
- Kaggle
| language: | |
| - fa | |
| license: mit | |
| ***This model is intended for non-commercial use only. If you wish to use it commercially, please refer to this LinkedIn address. | |
| https://www.linkedin.com/in/amin-rahmani-41417b121/ | |
| "Viravirast" is an editor based on transformer algorithms. By visiting Viravirast.com, you can use a Persian semantic and structural text editor. | |
| ***Use this code in order to get the complete and correct sentence | |
| from transformers import ( | |
| T5Tokenizer, | |
| MT5ForConditionalGeneration, | |
| Text2TextGenerationPipeline, | |
| ) | |
| path = "" | |
| pipe = Text2TextGenerationPipeline( | |
| model=MT5ForConditionalGeneration.from_pretrained(path), | |
| tokenizer=T5Tokenizer.from_pretrained(path), | |
| ) | |
| sentence = "ویراویراست یک نرم افزار ویرایش متن ساختاری و معنایی زبان فارسی است چیزی شبیه به گرامرلی در زبان انگلیسی" | |
| #res = pipe(sentence, max_length=100, num_beams=4 | |
| res = pipe(sentence, max_length=100) | |
| print(res[0]['generated_text']) | |
| n_epochs = 4 | |
| train_batch_size = 8 | |
| eval_batch_size = 4 | |
| lr = 5e-4 | |
| Training_Loss=0.00550 | |
| Validation_Loss=0.052046 | |