Edit on GitHub
  • John Snow Labs
  • Sep 19, 2024

Hindi whisper_tiny_finetune_hindi_fleurs_pipeline pipeline WhisperForCTC from Aryan-401

  • hi
  • open_source
  • pipeline
  • onnx

Description

Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.whisper_tiny_finetune_hindi_fleurs_pipeline is a Hindi model originally trained by Aryan-401.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("whisper_tiny_finetune_hindi_fleurs_pipeline", lang = "hi")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("whisper_tiny_finetune_hindi_fleurs_pipeline", lang = "hi")
val annotations = pipeline.transform(df)

Model Information

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

References

https://huggingface.co/Aryan-401/whisper-tiny-finetune-hindi-fleurs

Included Models

  • AudioAssembler
  • WhisperForCTC