# Multi-dataset Adaptation

This is a cross-encoder model fine-tuned from nreimers/MiniLM-L6-H384-uncased, designed for computing scores of text pairs, suitable for text re-ranking and semantic search tasks.

BART Large CNN is a pre-trained model based on the BART architecture, specifically designed for text summarization tasks.

A model fine-tuned from FewNERD-fine-supervised based on numind/NuNER-v1.0 for recognizing organizational entities (ORG) in text

A reward model trained based on human feedback, used to predict answers preferred by humans

This is a large Conformer-Transducer model for German automatic speech recognition, with approximately 120 million parameters, supporting the transcription of German speech into text.

PEGASUS is an abstractive summarization model pre-trained with gap sentences, developed by Google Research.

Brazilian Portuguese Wav2vec 2.0 speech recognition model fine-tuned on the LaPS BM dataset

DistilBART is a distilled version of the BART model, focusing on text summarization tasks, significantly reducing model size and inference time while maintaining high performance.

PEGASUS is a pre-trained abstractive summarization model based on gap sentence extraction, optimized for summarization generation through hybrid and randomization strategies

Wav2vec 2.0 model fine-tuned for Brazilian Portuguese speech recognition based on Common Voice 7.0 dataset

DistilBART is a distilled version of the BART model, focusing on text summarization tasks, significantly reducing model size and inference time while maintaining high performance.

This is a Wav2vec 2.0 model fine-tuned for Brazilian Portuguese, trained using the Sidney dataset, suitable for automatic speech recognition tasks in Brazilian Portuguese.