Whisper model released by the Swedish National Library, optimized for Swedish, trained on 50,000+ hours of Swedish speech data, outperforming the original OpenAI version

Audio ProcessingTransformersOther

A Whisper model trained on over 50,000 hours of Swedish speech data released by the National Library of Sweden, excelling in Swedish speech recognition tasks

Audio ProcessingTransformersOther

A Swedish speech recognition model based on the Whisper architecture released by the National Library of Sweden. The training data exceeds 50,000 hours, significantly reducing the word error rate.

Audio ProcessingTransformersOther

KB-Whisper Base is a Swedish speech recognition model released by the National Library of Sweden. Based on OpenAI's Whisper architecture, it is trained on over 50,000 hours of Swedish speech data. Compared with OpenAI's whisper-large-v3 model, it reduces the word error rate (WER) by an average of 47%, significantly improving the accuracy of Swedish speech recognition.

Audio ProcessingTransformersOther

NB-Whisper Small is a Norwegian speech recognition model developed by the National Library of Norway, based on OpenAI's Whisper model. This model has been trained for 250,000 steps using a diverse dataset containing 8 million samples, with a total duration of 66,000 hours. It supports automatic speech recognition and speech translation tasks for Norwegian (including written Norwegian and Nynorsk) and English.

Audio ProcessingTransformersMultiple Languages

Swedish BERT base model released by the National Library of Sweden/KBLab, trained on multi-source text data

Natural Language ProcessingJaxOther

Spanish Q&A model, fine-tuned from roberta-base-bne, pre-trained on 570GB of text data from the Spanish National Library

Natural Language ProcessingTransformersSpanish

GPT2-large Spanish language model trained on data from the National Library of Spain (BNE)

Natural Language ProcessingTransformersSpanish

This model is a Spanish named entity recognition model based on the RoBERTa architecture, pretrained on the large-scale corpus from the Spanish National Library and fine-tuned on the CAPITEL NER dataset.

Natural Language ProcessingTransformersMultiple Languages

This is a Spanish language model based on the GPT-2 architecture, trained using web-crawled data from the Spanish National Library between 2009 and 2019.

Natural Language ProcessingTransformersSpanish

A RoBERTa-large model trained on data from the Spanish National Library (BNE), fine-tuned for Spanish POS tagging on the CAPITEL dataset

Natural Language ProcessingTransformersMultiple Languages

Large Spanish language model trained on data from the National Library of Spain (BNE)

Natural Language ProcessingTransformersSpanish