Edit on GitHub
  • John Snow Labs
  • Sep 16, 2024

Arabic whisper_base_arabic_yazansalameh_pipeline pipeline WhisperForCTC from YazanSalameh

  • ar
  • open_source
  • pipeline
  • onnx

Description

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

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("whisper_base_arabic_yazansalameh_pipeline", lang = "ar")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("whisper_base_arabic_yazansalameh_pipeline", lang = "ar")
val annotations = pipeline.transform(df)

Model Information

Model Name: whisper_base_arabic_yazansalameh_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: ar
Size: 641.7 MB

References

https://huggingface.co/YazanSalameh/Whisper-base-Arabic

Included Models

  • AudioAssembler
  • WhisperForCTC