![]() This annotator is compatible with all the models trained/fine-tuned by using `TapasForQuestionAnswering` for **PyTorch** or `TFTapasForQuestionAnswering` for **TensorFlow** models in HuggingFace □ TAPAS is a BERT-based model specifically designed (and pre-trained) for answering questions about tabular data. for SQA, WTQ or WikiSQL-supervised tasks. `TapasForQuestionAnswering` can load TAPAS Models with a cell selection head and optional aggregation head on top for question-answering tasks on tables (linear layers on top of the hidden-states output to compute logits and optional logits_aggregation), e.g. * **NEW:** Introducing **TapasForQuestionAnswering** annotator in Spark NLP □. This annotator is compatible with all the models trained/fine-tuned by using `Wav2Vec2ForCTC` for **PyTorch** or `TFWav2Vec2ForCTC` for **TensorFlow** models in HuggingFace □ () It's the first multi-modal model of its kind we welcome in Spark NLP. Wav2Vec2 is a multi-modal model, that combines speech and text. ![]() `Wav2Vec2ForCTC` can load `Wav2Vec2` models for the Automatic Speech Recognition (ASR) task. ![]() * **NEW:** Introducing **Wav2Vec2ForCTC** annotator in Spark NLP □. * Fix exception in ContextSpellCheckerModel when updateVocabClass is used with append set to true * Fix feeding `fullAnnotate` in Lightpipeline with a list that started to fail in 4.2.0 release * Add SpanBertCoref annotator to all docs * Improve error handling in fullAnnotateImage for LightPipeline * Add support for Double type in addition to Float type to AudioAssembler annotator * Add support for Audio/ASR (Wav2Vec2) support to LightPipeline Add `enableRegexTokenizer` feature in WordSegmenter to support word segmentation within mixed and multi-lingual content * Support for multi-lingual WordSegmenter. * Fix missing indexes in `RecursiveTokenizer` annotator * Unify `annotatorType` name in Python and Scala for Spark schema in Annotation, AnnotationImage and AnnotationAudio * Add `Predicted Entities` to all Vision Transformers (ViT) models and pipelines * Add support for QA in `fullAnnotate` method in `PretrainedPipeline` * Add `fullAnnotateImageJava` to `PretrainedPipeline` for Java * Add `fullAnnotateImage` to `PretrainedPipeline` for Scala * Add `fullAnnotateJava` method in `PretrainedPipeline` for Java * Add `fullAnnotate` method in `PretrainedPipeline` for Scala * Add support for `fullAnnotate` in `LightPipeline` for path of images in Scala * Add support for importing TensorFlow SavedModel from remote storages like DBFS, S3, and HDFS
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |