Description
Pretrained BertForSequenceClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.toxic_comment_classification_pipeline is a Portuguese model originally trained by dougtrajano.
How to use
pipeline = PretrainedPipeline("toxic_comment_classification_pipeline", lang = "pt")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("toxic_comment_classification_pipeline", lang = "pt")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | toxic_comment_classification_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | pt |
| Size: | 1.3 GB |
References
https://huggingface.co/dougtrajano/toxic-comment-classification
Included Models
- DocumentAssembler
- TokenizerModel
- BertForSequenceClassification