Davlan

--- license: afl-3.0 --- Hugging Face's logo --- language: - ar - de - en - es - fr - it - lv - nl - pt - zh - multilingual

Hugging Face's logo m2m100418M-eng-yor-mt Model description m2m100418M-eng-yor-mt is a machine translation model from English language to Yorùbá language based on a fine-tuned facebook/m2m100418M model. It establishes a strong baseline for automatically translating texts from English to Yorùbá. Specifically, this model is a facebook/m2m100418M model that was fine-tuned on JW300 Yorùbá corpus and Menyo-20k. Limitations and bias This model is limited by its training dataset. This may not generalize well for all use cases in different domains. Training data This model was fine-tuned on JW300 corpus and Menyo-20k dataset Training procedure This model was trained on NVIDIA V100 GPU Eval results on Test set (BLEU score) Fine-tuning m2m100418M achieves 13.39 BLEU on Menyo-20k test set while mt5-base achieves 9.82

Hugging Face's logo byt5-base-eng-yor-mt Model description byt5-base-eng-yor-mt is a machine translation model from English language to Yorùbá language based on a fine-tuned byt5-base model. It establishes a strong baseline for automatically translating texts from English to Yorùbá. Specifically, this model is a byt5-base model that was fine-tuned on JW300 Yorùbá corpus and Menyo-20k Limitations and bias This model is limited by its training dataset. This may not generalize well for all use cases in different domains. Training data This model was fine-tuned on on JW300 corpus and Menyo-20k dataset Training procedure This model was trained on NVIDIA V100 GPU Eval results on Test set (BLEU score) Fine-tuning byt5-base achieves 12.23 BLEU on Menyo-20k test set while mt5-base achieves 9.82

Hugging Face's logo mbart50-large-yor-eng-mt Model description mbart50-large-yor-eng-mt is a machine translation model from Yorùbá language to English language based on a fine-tuned facebook/mbart-large-50 model. It establishes a strong baseline for automatically translating texts from Yorùbá to English. Specifically, this model is a mbart-large-50 model that was fine-tuned on JW300 Yorùbá corpus and Menyo-20k. The model was trained using Swahili(swKE) as the language since the pre-trained model does not initially support Yorùbá. Thus, you need to use the swKE for language code when evaluating the model. Limitations and bias This model is limited by its training dataset. This may not generalize well for all use cases in different domains. Training data This model was fine-tuned on on JW300 corpus and Menyo-20k dataset Training procedure This model was trained on NVIDIA V100 GPU Eval results on Test set (BLEU score) Fine-tuning mbart50-large achieves 15.88 BLEU on Menyo-20k test set while mt5-base achieves 15.57

Hugging Face's logo bert-base-multilingual-cased-finetuned-yoruba Model description bert-base-multilingual-cased-finetuned-yoruba is a Yoruba BERT model obtained by fine-tuning bert-base-multilingual-cased model on Yorùbá language texts. It provides better performance than the multilingual BERT on text classification and named entity recognition datasets. Specifically, this model is a bert-base-multilingual-cased model that was fine-tuned on Yorùbá corpus. Intended uses & limitations How to use You can use this model with Transformers pipeline for masked token prediction. Limitations and bias This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains. Training data This model was fine-tuned on Bible, JW300, Menyo-20k, Yoruba Embedding corpus and CC-Aligned, Wikipedia, news corpora (BBC Yoruba, VON Yoruba, Asejere, Alaroye), and other small datasets curated from friends. Training procedure This model was trained on a single NVIDIA V100 GPU Eval results on Test set (F-score, average over 5 runs) Dataset| mBERT F1 | yobert F1 -|-|- MasakhaNER | 78.97 | 82.58 BBC Yorùbá Textclass | 75.13 | 79.11

Hugging Face's logo mT5baseyorubaadr Model description mT5baseyorubaadr is a automatic diacritics restoration model for Yorùbá language based on a fine-tuned mT5-base model. It achieves the state-of-the-art performance for adding the correct diacritics or tonal marks to Yorùbá texts. Specifically, this model is a mT5base model that was fine-tuned on JW300 Yorùbá corpus and Menyo-20k Intended uses & limitations How to use You can use this model with Transformers pipeline for ADR. Limitations and bias This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains. Training data This model was fine-tuned on on JW300 Yorùbá corpus and Menyo-20k dataset Training procedure This model was trained on a single NVIDIA V100 GPU Eval results on Test set (BLEU score) 64.63 BLEU on Global Voices test set 70.27 BLEU on Menyo-20k test set BibTeX entry and citation info By Jesujoba Alabi and David Adelani

Hugging Face's logo m2m100418M-eng-yor-mt Model description m2m100418M-yor-eng-mt is a machine translation model from Yorùbá language to English language based on a fine-tuned facebook/m2m100418M model. It establishes a strong baseline for automatically translating texts from Yorùbá to English. Specifically, this model is a facebook/m2m100418M model that was fine-tuned on JW300 Yorùbá corpus and Menyo-20k. Limitations and bias This model is limited by its training dataset. This may not generalize well for all use cases in different domains. Training data This model was fine-tuned on JW300 corpus and Menyo-20k dataset Training procedure This model was trained on NVIDIA V100 GPU Eval results on Test set (BLEU score) Fine-tuning m2m100418M achieves 16.76 BLEU on Menyo-20k test set while mt5-base achieves 15.57

Hugging Face's logo mT5baseengyormt Model description mT5baseyorengmt is a machine translation model from English language to Yorùbá language based on a fine-tuned mT5-base model. It establishes a strong baseline for automatically translating texts from English to Yorùbá. Specifically, this model is a mT5base model that was fine-tuned on JW300 Yorùbá corpus and Menyo-20k Intended uses & limitations How to use You can use this model with Transformers pipeline for MT. Limitations and bias This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains. Training data This model was fine-tuned on on JW300 corpus and Menyo-20k dataset Training procedure This model was trained on a single NVIDIA V100 GPU Eval results on Test set (BLEU score) 9.82 BLEU on Menyo-20k test set

Hugging Face's logo byt5-base-yor-eng-mt Model description byt5-base-yor-eng-mt is a machine translation model from Yorùbá language to English language based on a fine-tuned byt5-base model. It establishes a strong baseline for automatically translating texts from Yorùbá to English. Specifically, this model is a byt5-base model that was fine-tuned on JW300 Yorùbá corpus and Menyo-20k Limitations and bias This model is limited by its training dataset. This may not generalize well for all use cases in different domains. Training data This model was fine-tuned on on JW300 corpus and Menyo-20k dataset Training procedure This model was trained on NVIDIA V100 GPU Eval results on Test set (BLEU score) Fine-tuning byt5-base achieves 14.05 BLEU on Menyo-20k test set while mt5-base achieves 15.57

Hugging Face's logo mbart50-large-eng-yor-mt Model description mbart50-large-eng-yor-mt is a machine translation model from English language to Yorùbá language based on a fine-tuned facebook/mbart-large-50 model. It establishes a strong baseline for automatically translating texts from English to Yorùbá. Specifically, this model is a mbart-large-50 model that was fine-tuned on JW300 Yorùbá corpus and Menyo-20k. The model was trained using Swahili(swKE) as the language since the pre-trained model does not initially support Yorùbá. Thus, you need to use the swKE for language code when evaluating the model. Limitations and bias This model is limited by its training dataset. This may not generalize well for all use cases in different domains. Training data This model was fine-tuned on on JW300 corpus and Menyo-20k dataset Training procedure This model was trained on NVIDIA V100 GPU Eval results on Test set (BLEU score) Fine-tuning mbarr50-large achieves 13.39 BLEU on Menyo-20k test set while mt5-base achieves 9.82