Edit on GitHub
  • John Snow Labs
  • Sep 20, 2024

Multilingual whisper_tiny_finetuned_multilingual_5_languages_pipeline pipeline WhisperForCTC from Prasetyow12

  • xx
  • open_source
  • pipeline
  • onnx

Description

Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.whisper_tiny_finetuned_multilingual_5_languages_pipeline is a Multilingual model originally trained by Prasetyow12.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("whisper_tiny_finetuned_multilingual_5_languages_pipeline", lang = "xx")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("whisper_tiny_finetuned_multilingual_5_languages_pipeline", lang = "xx")
val annotations = pipeline.transform(df)

Model Information

Model Name: whisper_tiny_finetuned_multilingual_5_languages_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: xx
Size: 390.0 MB

References

https://huggingface.co/Prasetyow12/whisper-tiny-finetuned-multilingual-5-languages

Included Models

  • AudioAssembler
  • WhisperForCTC