# Low-resource language

Latxa is a 70B-parameter Basque language large language model based on Llama-3.1, fine-tuned with instructions and FP8 quantization, specifically optimized for Basque

Latxa is a Basque language instruction-tuned large language model based on the Llama-3.1 architecture, specifically optimized for Basque, demonstrating excellent performance across multiple benchmarks.

Urdu TTS model fine-tuned from microsoft/speecht5_tts with small training dataset (4,200 sentences). Commercial use requires retraining.

This is a machine translation model fine-tuned based on Meta's NLLB-200 model, specifically designed for bidirectional translation tasks between Wolof and French.

This is a sequence-to-sequence model for translating Bengali to English.

This is a fine-tuned English-to-Arabic translation model based on Helsinki-NLP/opus-mt-en-ar, trained on a dataset of 120,000 entries with a Bleu score of 20.6264.

Hungarian abstractive summarization model based on mT5-base architecture, trained on HunSum-1 dataset

Indonesian Q&A model fine-tuned on the SQuAD2.0 dataset based on IndoBERT

Urdu speech recognition model based on the wav2vec2-large-xls-r-300m architecture, fine-tuned on the Common Voice dataset

A speech recognition model fine-tuned for Irish language using the Common Voice dataset, based on facebook/wav2vec2-large-xlsr-53.

This is a Mongolian text generation model based on the GPT2 architecture, designed to generate fluent Mongolian text.

This is a Kalmyk automatic speech recognition model based on the Wav2Vec2 architecture, pre-trained and fine-tuned to support Kalmyk speech-to-text tasks.

Bidirectional translation model for Sinhala-English based on fine-tuned mT5-base

An automatic speech recognition model fine-tuned for Lithuanian using the Common Voice dataset, based on the facebook/wav2vec2-large-xlsr-53 model.

A Punjabi automatic speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, supporting 16kHz sample rate input.

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the Common Voice dataset, supporting Guarani speech recognition.

An automatic speech recognition model fine-tuned for Mongolian using the Common Voice dataset, based on the facebook/wav2vec2-large-xlsr-53 model.

This model is an automatic speech recognition model fine-tuned on the Common Voice 8 Chuvash dataset based on facebook/wav2vec2-xls-r-1b

This is a machine translation model based on the Transformer architecture, specifically designed for translating French (fr) to Shona (sn).

This is an Irish-to-English machine translation model based on the transformer-align architecture, released by Tatoeba-Challenge.

This is a Transformer-based machine translation model for Luganda (lg) to English (en), developed by the Helsinki-NLP team.

This is a Hausa-to-English machine translation model based on the Transformer architecture, developed by the Helsinki-NLP team.

OPUS-MT provided Northern Sotho (nso) to English (en) machine translation model, based on Transformer architecture and SentencePiece preprocessing

This is a machine translation model based on the Transformer architecture, specifically designed for translating Kabyle (kab) to English (en).

A German-to-Ga machine translation model provided by the OPUS-MT project, implemented based on the Transformer architecture.

This is a Transformer-based machine translation model from Yoruba to English, developed by the Helsinki-NLP team.

This is a Transformer-based machine translation model specifically designed for translating Samoan (sm) to English (en).

This is a machine translation model based on the Transformer architecture, specifically designed for translating Tswana (tn) to English (en).

Transformer-based machine translation model for Chichewa (ny) to English (en), developed by Helsinki-NLP team

Hausa automatic speech recognition model based on wav2vec2-xls-r-300m architecture, fine-tuned on Common Voice 8.0 Hausa dataset

Transformer-based Oromo (om) to English (en) machine translation model developed by Helsinki-NLP team

A Transformer-based machine translation model for translating Wallisian (wls) to English (en).

This is a Transformer-based machine translation model specifically designed for translating Hiligaynon to English.