Token Classification
Transformers
Safetensors
Malagasy
xlm-roberta
punctuation-restoration
truecasing
malagasy
asr-postprocessing
Instructions to use Flo976/malagasy-punctuation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Flo976/malagasy-punctuation with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Flo976/malagasy-punctuation")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Flo976/malagasy-punctuation") model = AutoModelForTokenClassification.from_pretrained("Flo976/malagasy-punctuation", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from Flo976/malagasy-punctuation: direct link, hf CLI and curl.
- Browser
- Download file 1.59 kB
-
https://huggingface.co/Flo976/malagasy-punctuation/resolve/main/config.json
- Command line
-
hf download hf://Flo976/malagasy-punctuation/config.json
-
curl -L -o config.json https://huggingface.co/Flo976/malagasy-punctuation/resolve/main/config.json
1.59 kB
| { | |
| "architectures": [ | |
| "XLMRobertaForTokenClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "L|O", | |
| "1": "L|,", | |
| "2": "L|.", | |
| "3": "L|?", | |
| "4": "L|!", | |
| "5": "L|:", | |
| "6": "L|;", | |
| "7": "C|O", | |
| "8": "C|,", | |
| "9": "C|.", | |
| "10": "C|?", | |
| "11": "C|!", | |
| "12": "C|:", | |
| "13": "C|;", | |
| "14": "U|O", | |
| "15": "U|,", | |
| "16": "U|.", | |
| "17": "U|?", | |
| "18": "U|!", | |
| "19": "U|:", | |
| "20": "U|;", | |
| "21": "M|O", | |
| "22": "M|,", | |
| "23": "M|.", | |
| "24": "M|?", | |
| "25": "M|!", | |
| "26": "M|:", | |
| "27": "M|;" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "C|!": 11, | |
| "C|,": 8, | |
| "C|.": 9, | |
| "C|:": 12, | |
| "C|;": 13, | |
| "C|?": 10, | |
| "C|O": 7, | |
| "L|!": 4, | |
| "L|,": 1, | |
| "L|.": 2, | |
| "L|:": 5, | |
| "L|;": 6, | |
| "L|?": 3, | |
| "L|O": 0, | |
| "M|!": 25, | |
| "M|,": 22, | |
| "M|.": 23, | |
| "M|:": 26, | |
| "M|;": 27, | |
| "M|?": 24, | |
| "M|O": 21, | |
| "U|!": 18, | |
| "U|,": 15, | |
| "U|.": 16, | |
| "U|:": 19, | |
| "U|;": 20, | |
| "U|?": 17, | |
| "U|O": 14 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "xlm-roberta", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "transformers_version": "4.57.1", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 250002 | |
| } | |