Edit on GitHub
  • John Snow Labs
  • Apr 01, 2023

English asr_swin_hubert_large_ls960_ft_timit TFHubertForCTC from obokkkk

  • hubert
  • en
  • open_source
  • audio
  • asr
  • pipeline

Description

Pretrained Hubert pipeline, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_swin_hubert_large_ls960_ft_timit is a English model originally trained by obokkkk.

Download Copy S3 URI

How to use


    pipeline = PretrainedPipeline('pipeline_asr_swin_hubert_large_ls960_ft_timit', lang = 'en')
    annotations =  pipeline.transform(audioDF)
    


    val pipeline = new PretrainedPipeline("pipeline_asr_swin_hubert_large_ls960_ft_timit", lang = "en")
    val annotations = pipeline.transform(audioDF)

Model Information

Model Name: pipeline_asr_swin_hubert_large_ls960_ft_timit
Type: pipeline
Compatibility: Spark NLP 4.4.0+
License: Open Source
Edition: Official
Language: en
Size: 2.4 GB

Included Models

  • AudioAssembler
  • HubertForCTC