Edit on GitHub
  • John Snow Labs
  • Dec 17, 2024

German whisper_large_german_pipeline pipeline WhisperForCTC from Krish03

  • de
  • open_source
  • pipeline
  • onnx

Description

Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.whisper_large_german_pipeline is a German model originally trained by Krish03.

Download Copy S3 URI

How to use


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



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

Model Information

Model Name: whisper_large_german_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: de
Size: 642.2 MB

References

https://huggingface.co/Krish03/whisper-large-de

Included Models

  • AudioAssembler
  • WhisperForCTC