Edit on GitHub
  • John Snow Labs
  • Feb 07, 2025

German wav2vec2_large_xlsr_53_german_facebook_pipeline pipeline Wav2Vec2ForCTC from facebook

  • de
  • open_source
  • pipeline
  • onnx

Description

Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.wav2vec2_large_xlsr_53_german_facebook_pipeline is a German model originally trained by facebook.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("wav2vec2_large_xlsr_53_german_facebook_pipeline", lang = "de")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("wav2vec2_large_xlsr_53_german_facebook_pipeline", lang = "de")
val annotations = pipeline.transform(df)

Model Information

Model Name: wav2vec2_large_xlsr_53_german_facebook_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: de
Size: 766.2 MB

References

https://huggingface.co/facebook/wav2vec2-large-xlsr-53-german

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC