Edit on GitHub
  • John Snow Labs
  • Apr 09, 2025

Bulgarian wav2vec2_large_xls_r_300m_bulgarian_v1_pipeline pipeline Wav2Vec2ForCTC from DrishtiSharma

  • bg
  • open_source
  • pipeline
  • onnx

Description

Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.wav2vec2_large_xls_r_300m_bulgarian_v1_pipeline is a Bulgarian model originally trained by DrishtiSharma.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("wav2vec2_large_xls_r_300m_bulgarian_v1_pipeline", lang = "bg")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("wav2vec2_large_xls_r_300m_bulgarian_v1_pipeline", lang = "bg")
val annotations = pipeline.transform(df)

Model Information

Model Name: wav2vec2_large_xls_r_300m_bulgarian_v1_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: bg
Size: 1.2 GB

References

https://huggingface.co/DrishtiSharma/wav2vec2-large-xls-r-300m-bg-v1

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC