Japanese whisper_small_jp_pipeline pipeline WhisperForCTC from kimbochen

Description

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

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("whisper_small_jp_pipeline", lang = "ja")
annotations =  pipeline.transform(df)   


val pipeline = new PretrainedPipeline("whisper_small_jp_pipeline", lang = "ja")
val annotations = pipeline.transform(df)

Model Information

Model Name: whisper_small_jp_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: ja
Size: 1.7 GB

References

https://huggingface.co/kimbochen/whisper-small-jp

Included Models

  • AudioAssembler
  • WhisperForCTC