datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
tajik-namesThis dataset comprises a collection of traditional Tajik names, sourced from the Catalogue of Tajik National Names. It includes a variety of names along with their translations and descriptions. The dataset is designed to serve as a resource for linguistic and cultural studies, providing insights into naming conventions and practices in Tajik culture.
Columns:
Number: A unique identifier for each name entry.
Tajik: The name in the Tajik language.
Russian: The Russian transliteration of the… See the full description on the dataset page: https://huggingface.co/datasets/sobir-hf/tajik-names.tajik_lemmastajik-farsi-transliteration-benchmark
🇹🇯🇮🇷 Tajik-Farsi Transliteration Benchmark
Официальный бенчмарк машинной транслитерации между таджикским (кириллица) и фарси (персо-арабская графика).Результаты получены на 40k параллельных предложениях с оценкой по 3 случайным сидам, bootstrap 95% CI и парными статистическими тестами.
📊 Ключевые результаты (Top-5)
Модель
Направление
chrF++
BLEU
CER
byt5-small
Tj→Fa
87.35 ± 0.10
73.58
0.054
byt5-small
Fa→Tj
80.07 ± 0.23
56.61
0.090
G2PTransformer
Tj→Fa… See the full description on the dataset page: https://huggingface.co/datasets/TajikNLPWorld/tajik-farsi-transliteration-benchmark.