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

German asr_swin_exp_w2v2t_de_hubert_s126 TFHubertForCTC from jonatasgrosman

  • hubert
  • de
  • 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_exp_w2v2t_de_hubert_s126 is a German model originally trained by jonatasgrosman.

Download Copy S3 URI

How to use


    pipeline = PretrainedPipeline('pipeline_asr_swin_exp_w2v2t_de_hubert_s126', lang = 'de')
    annotations =  pipeline.transform(audioDF)
    


    val pipeline = new PretrainedPipeline("pipeline_asr_swin_exp_w2v2t_de_hubert_s126", lang = "de")
    val annotations = pipeline.transform(audioDF)

Model Information

Model Name: pipeline_asr_swin_exp_w2v2t_de_hubert_s126
Type: pipeline
Compatibility: Spark NLP 4.4.0+
License: Open Source
Edition: Official
Language: de
Size: 2.4 GB

Included Models

  • AudioAssembler
  • HubertForCTC