Edit on GitHub
  • John Snow Labs
  • Sep 23, 2024

Korean whisper_small_child50k_timestretch_steplr_pipeline pipeline WhisperForCTC from haseong8012

  • ko
  • open_source
  • pipeline
  • onnx

Description

Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.whisper_small_child50k_timestretch_steplr_pipeline is a Korean model originally trained by haseong8012.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("whisper_small_child50k_timestretch_steplr_pipeline", lang = "ko")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("whisper_small_child50k_timestretch_steplr_pipeline", lang = "ko")
val annotations = pipeline.transform(df)

Model Information

Model Name: whisper_small_child50k_timestretch_steplr_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: ko
Size: 1.7 GB

References

https://huggingface.co/haseong8012/whisper-small_child50K_timestretch_stepLR

Included Models

  • AudioAssembler
  • WhisperForCTC