Edit on GitHub
  • John Snow Labs
  • Oct 18, 2023

Tamil asr_whisper_tiny_tamil_example_pipeline pipeline WhisperForCTC from parambharat

  • whisper
  • ta
  • open_source
  • pipeline

Description

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

This model is only compatible with PySpark 3.4 and above

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline('asr_whisper_tiny_tamil_example_pipeline', lang = 'ta')
annotations =  pipeline.transform(audioDF)



val pipeline = new PretrainedPipeline('asr_whisper_tiny_tamil_example_pipeline', lang = 'ta')
val annotations = pipeline.transform(audioDF)

Model Information

Model Name: asr_whisper_tiny_tamil_example_pipeline
Type: pipeline
Compatibility: Spark NLP 5.1.4+
License: Open Source
Edition: Official
Language: ta
Size: 390.9 MB

References

https://huggingface.co/parambharat/whisper-tiny-ta-example

Included Models

  • AudioAssembler
  • WhisperForCTC