Edit on GitHub
  • John Snow Labs
  • Oct 17, 2023

French asr_whisper_small_defined_dot_ai_qc_french_combined_dataset_normalized_pipeline pipeline WhisperForCTC from jwkritchie

  • whisper
  • fr
  • open_source
  • pipeline

Description

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

This model is only compatible with PySpark 3.4 and above

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline('asr_whisper_small_defined_dot_ai_qc_french_combined_dataset_normalized_pipeline', lang = 'fr')
annotations =  pipeline.transform(audioDF)



val pipeline = new PretrainedPipeline('asr_whisper_small_defined_dot_ai_qc_french_combined_dataset_normalized_pipeline', lang = 'fr')
val annotations = pipeline.transform(audioDF)

Model Information

Model Name: asr_whisper_small_defined_dot_ai_qc_french_combined_dataset_normalized_pipeline
Type: pipeline
Compatibility: Spark NLP 5.1.4+
License: Open Source
Edition: Official
Language: fr
Size: 1.7 GB

References

https://huggingface.co/jwkritchie/whisper-small-defined-dot-ai-qc-fr-combined-dataset-normalized

Included Models

  • AudioAssembler
  • WhisperForCTC