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

Korean speech_impediment_audio_pipeline pipeline WhisperForCTC from yoona-J

  • ko
  • open_source
  • pipeline
  • onnx

Description

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

Download Copy S3 URI

How to use


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



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

Model Information

Model Name: speech_impediment_audio_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: ko
Size: 642.4 MB

References

https://huggingface.co/yoona-J/speech_impediment_audio

Included Models

  • AudioAssembler
  • WhisperForCTC