Korean wav2vec2_xls_r_300m_korean_lm_pipeline pipeline Wav2Vec2ForCTC from w11wo

Description

Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.wav2vec2_xls_r_300m_korean_lm_pipeline is a Korean model originally trained by w11wo.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("wav2vec2_xls_r_300m_korean_lm_pipeline", lang = "ko")
annotations =  pipeline.transform(df)   


val pipeline = new PretrainedPipeline("wav2vec2_xls_r_300m_korean_lm_pipeline", lang = "ko")
val annotations = pipeline.transform(df)

Model Information

Model Name: wav2vec2_xls_r_300m_korean_lm_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: ko
Size: 1.2 GB

References

https://huggingface.co/w11wo/wav2vec2-xls-r-300m-korean-lm

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC