Edit on GitHub
  • John Snow Labs
  • Oct 17, 2023

Czech asr_whisper_small_czech_cv11_pipeline pipeline WhisperForCTC from mikr

  • whisper
  • cs
  • open_source
  • pipeline

Description

Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_whisper_small_czech_cv11_pipeline is a Czech model originally trained by mikr.

This model is only compatible with PySpark 3.4 and above

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline('asr_whisper_small_czech_cv11_pipeline', lang = 'cs')
annotations =  pipeline.transform(audioDF)



val pipeline = new PretrainedPipeline('asr_whisper_small_czech_cv11_pipeline', lang = 'cs')
val annotations = pipeline.transform(audioDF)

Model Information

Model Name: asr_whisper_small_czech_cv11_pipeline
Type: pipeline
Compatibility: Spark NLP 5.1.4+
License: Open Source
Edition: Official
Language: cs
Size: 1.7 GB

References

https://huggingface.co/mikr/whisper-small-cs-cv11

Included Models

  • AudioAssembler
  • WhisperForCTC