Token Classification
Transformers
PyTorch
Safetensors
Hungarian
bert
punctuation
punctuation_restoration
hungarian
hungarian web corpus
punctuation restoration
központozás
Instructions to use gyenist/hupunct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gyenist/hupunct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="gyenist/hupunct")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("gyenist/hupunct") model = AutoModelForTokenClassification.from_pretrained("gyenist/hupunct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from gyenist/hupunct: direct link, hf CLI and curl.
- Browser
- Download file 125 Bytes
-
https://huggingface.co/gyenist/hupunct/resolve/d4bf78f02c2a75e65280bc04b97f9fd41e80f9d1/special_tokens_map.json
- Command line
-
hf download hf://gyenist/hupunct@d4bf78f02c2a75e65280bc04b97f9fd41e80f9d1/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/gyenist/hupunct/resolve/d4bf78f02c2a75e65280bc04b97f9fd41e80f9d1/special_tokens_map.json
125 Bytes
| { | |
| "cls_token": "[CLS]", | |
| "mask_token": "[MASK]", | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "unk_token": "[UNK]" | |
| } | |