--- language: - ur license: apache-2.0 library_name: transformers tags: - part-of-speech - token-classification datasets: - universal_dependencies metrics: - accuracy model-index: - name: xlm-roberta-base-ft-udpos28-ur results: - task: type: token-classification name: Part-of-Speech Tagging dataset: type: universal_dependencies name: Universal Dependencies v2.8 metrics: - type: accuracy name: English Test accuracy value: 76.9 - type: accuracy name: Dutch Test accuracy value: 74.3 - type: accuracy name: German Test accuracy value: 73.5 - type: accuracy name: Italian Test accuracy value: 71.0 - type: accuracy name: French Test accuracy value: 68.2 - type: accuracy name: Spanish Test accuracy value: 72.7 - type: accuracy name: Russian Test accuracy value: 85.9 - type: accuracy name: Swedish Test accuracy value: 80.0 - type: accuracy name: Norwegian Test accuracy value: 74.9 - type: accuracy name: Danish Test accuracy value: 77.4 - type: accuracy name: Low Saxon Test accuracy value: 46.2 - type: accuracy name: Akkadian Test accuracy value: 19.5 - type: accuracy name: Armenian Test accuracy value: 82.7 - type: accuracy name: Welsh Test accuracy value: 63.7 - type: accuracy name: Old East Slavic Test accuracy value: 69.3 - type: accuracy name: Albanian Test accuracy value: 71.8 - type: accuracy name: Slovenian Test accuracy value: 74.0 - type: accuracy name: Guajajara Test accuracy value: 19.2 - type: accuracy name: Kurmanji Test accuracy value: 75.2 - type: accuracy name: Turkish Test accuracy value: 76.7 - type: accuracy name: Finnish Test accuracy value: 80.4 - type: accuracy name: Indonesian Test accuracy value: 78.0 - type: accuracy name: Ukrainian Test accuracy value: 83.8 - type: accuracy name: Polish Test accuracy value: 83.5 - type: accuracy name: Portuguese Test accuracy value: 74.5 - type: accuracy name: Kazakh Test accuracy value: 82.6 - type: accuracy name: Latin Test accuracy value: 72.6 - type: accuracy name: Old French Test accuracy value: 43.4 - type: accuracy name: Buryat Test accuracy value: 49.7 - type: accuracy name: Kaapor Test accuracy value: 15.8 - type: accuracy name: Korean Test accuracy value: 59.0 - type: accuracy name: Estonian Test accuracy value: 81.0 - type: accuracy name: Croatian Test accuracy value: 82.0 - type: accuracy name: Gothic Test accuracy value: 5.8 - type: accuracy name: Swiss German Test accuracy value: 43.1 - type: accuracy name: Assyrian Test accuracy value: 17.2 - type: accuracy name: North Sami Test accuracy value: 22.3 - type: accuracy name: Naija Test accuracy value: 36.3 - type: accuracy name: Latvian Test accuracy value: 82.3 - type: accuracy name: Chinese Test accuracy value: 33.9 - type: accuracy name: Tagalog Test accuracy value: 78.5 - type: accuracy name: Bambara Test accuracy value: 18.7 - type: accuracy name: Lithuanian Test accuracy value: 82.9 - type: accuracy name: Galician Test accuracy value: 73.5 - type: accuracy name: Vietnamese Test accuracy value: 60.4 - type: accuracy name: Greek Test accuracy value: 68.1 - type: accuracy name: Catalan Test accuracy value: 70.9 - type: accuracy name: Czech Test accuracy value: 81.0 - type: accuracy name: Erzya Test accuracy value: 31.3 - type: accuracy name: Bhojpuri Test accuracy value: 62.1 - type: accuracy name: Thai Test accuracy value: 46.9 - type: accuracy name: Marathi Test accuracy value: 82.2 - type: accuracy name: Basque Test accuracy value: 77.8 - type: accuracy name: Slovak Test accuracy value: 80.8 - type: accuracy name: Kiche Test accuracy value: 21.2 - type: accuracy name: Yoruba Test accuracy value: 16.4 - type: accuracy name: Warlpiri Test accuracy value: 19.8 - type: accuracy name: Tamil Test accuracy value: 86.0 - type: accuracy name: Maltese Test accuracy value: 15.1 - type: accuracy name: Ancient Greek Test accuracy value: 56.3 - type: accuracy name: Icelandic Test accuracy value: 74.4 - type: accuracy name: Mbya Guarani Test accuracy value: 22.7 - type: accuracy name: Urdu Test accuracy value: 94.8 - type: accuracy name: Romanian Test accuracy value: 74.7 - type: accuracy name: Persian Test accuracy value: 80.6 - type: accuracy name: Apurina Test accuracy value: 21.6 - type: accuracy name: Japanese Test accuracy value: 29.6 - type: accuracy name: Hungarian Test accuracy value: 72.6 - type: accuracy name: Hindi Test accuracy value: 91.9 - type: accuracy name: Classical Chinese Test accuracy value: 16.8 - type: accuracy name: Komi Permyak Test accuracy value: 32.5 - type: accuracy name: Faroese Test accuracy value: 67.3 - type: accuracy name: Sanskrit Test accuracy value: 12.1 - type: accuracy name: Livvi Test accuracy value: 51.9 - type: accuracy name: Arabic Test accuracy value: 79.8 - type: accuracy name: Wolof Test accuracy value: 21.6 - type: accuracy name: Bulgarian Test accuracy value: 84.7 - type: accuracy name: Akuntsu Test accuracy value: 15.4 - type: accuracy name: Makurap Test accuracy value: 2.1 - type: accuracy name: Kangri Test accuracy value: 55.4 - type: accuracy name: Breton Test accuracy value: 49.5 - type: accuracy name: Telugu Test accuracy value: 85.2 - type: accuracy name: Cantonese Test accuracy value: 38.2 - type: accuracy name: Old Church Slavonic Test accuracy value: 38.1 - type: accuracy name: Karelian Test accuracy value: 61.1 - type: accuracy name: Upper Sorbian Test accuracy value: 64.6 - type: accuracy name: South Levantine Arabic Test accuracy value: 61.6 - type: accuracy name: Komi Zyrian Test accuracy value: 27.6 - type: accuracy name: Irish Test accuracy value: 62.7 - type: accuracy name: Nayini Test accuracy value: 41.0 - type: accuracy name: Munduruku Test accuracy value: 8.7 - type: accuracy name: Manx Test accuracy value: 20.1 - type: accuracy name: Skolt Sami Test accuracy value: 25.0 - type: accuracy name: Afrikaans Test accuracy value: 74.0 - type: accuracy name: Old Turkish Test accuracy value: 44.3 - type: accuracy name: Tupinamba Test accuracy value: 20.9 - type: accuracy name: Belarusian Test accuracy value: 82.6 - type: accuracy name: Serbian Test accuracy value: 82.4 - type: accuracy name: Moksha Test accuracy value: 28.5 - type: accuracy name: Western Armenian Test accuracy value: 74.1 - type: accuracy name: Scottish Gaelic Test accuracy value: 53.3 - type: accuracy name: Khunsari Test accuracy value: 43.2 - type: accuracy name: Hebrew Test accuracy value: 83.3 - type: accuracy name: Uyghur Test accuracy value: 75.8 - type: accuracy name: Chukchi Test accuracy value: 26.8 --- # XLM-RoBERTa base Universal Dependencies v2.8 POS tagging: Urdu This model is part of our paper called: - Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages Check the [Space](https://huggingface.co./spaces/wietsedv/xpos) for more details. ## Usage ```python from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-ur") model = AutoModelForTokenClassification.from_pretrained("wietsedv/xlm-roberta-base-ft-udpos28-ur") ```