IndoT5 Machine Translation - a LazarusNLP Collection

LazarusNLP 's Collections

NusaBERT

Indonesian Sentence Embedding

Indonesian T5 Language Models

Indonesian Natural Language Inference

IndoT5 Machine Translation

updated May 11

Fine-tuned mT5 models on languages of Indonesia. Based on Many-to-Many Multilingual Translation Model for Languages of Indonesia (Wongso et al., 2023)

Upvote

LazarusNLP/indo-t5-base

Text2Text Generation • Updated Mar 21, 2023 • 48

Note mT5 fine-tuned on many-to-many parallel Bible texts in these languages: Acehnese, Balinese, Buginese, Indonesian, Javanese, Minangkabau, Sundanese.
LazarusNLP/indo-t5-base-nusax

Text2Text Generation • Updated about 23 hours ago • 34 • 1

Note A fine-tune of the above on many-to-many translation of NusaX dataset. Supports the same language as above.
LazarusNLP/indo-t5-base-v2

Text2Text Generation • Updated Mar 29, 2023 • 27 • 1

Note mT5 fine-tuned on parallel Bible texts in 45 languages: Abun, Acehnese, Ambonese, Anggurk Yali, Aralle-Tabulahan, Balantak, Balinese, Bambam, Batak Karo, Batak Simalungun, Bauzi, Berik, Buginese, Da'a Kaili, Duri, Ende, Galela, Gorontalo, Hawu, Iban, Indonesian, Javanese, Kupang, Lampung Api, Madurese, Makassarese, Mamasa, Manggarai, Mentawai, Meyah, Minangkabau, Mongondow, Napu, Ngaju, Nias, Pakpak Dairi, Pamona, Sangirese, Sasak, Sundanese, Tabaru, Termanu, Toba Batak, Toraja-Sa'dan, Uma, Yawa
LazarusNLP/indo-t5-base-v2-nusax

Text2Text Generation • Updated Apr 1, 2023 • 31

Note A fine-tune of the above on many-to-many translation of NusaX dataset. Supports the same language as above.

Upvote