Edit on GitHub
  • John Snow Labs
  • Apr 03, 2025

English facebook_wav2vec2_xls_r_300m_50h_pipeline pipeline Wav2Vec2ForCTC from namkyeong

  • en
  • open_source
  • pipeline
  • onnx

Description

Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.facebook_wav2vec2_xls_r_300m_50h_pipeline is a English model originally trained by namkyeong.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("facebook_wav2vec2_xls_r_300m_50h_pipeline", lang = "en")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("facebook_wav2vec2_xls_r_300m_50h_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: facebook_wav2vec2_xls_r_300m_50h_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 1.2 GB

References

https://huggingface.co/namkyeong/facebook_wav2vec2-xls-r-300m_50h

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC