Edit on GitHub
  • John Snow Labs
  • Apr 01, 2025

Japanese japanese_wav2vec2_large_rs35kh_pipeline pipeline Wav2Vec2ForCTC from reazon-research

  • ja
  • open_source
  • pipeline
  • onnx

Description

Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.japanese_wav2vec2_large_rs35kh_pipeline is a Japanese model originally trained by reazon-research.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("japanese_wav2vec2_large_rs35kh_pipeline", lang = "ja")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("japanese_wav2vec2_large_rs35kh_pipeline", lang = "ja")
val annotations = pipeline.transform(df)

Model Information

Model Name: japanese_wav2vec2_large_rs35kh_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: ja
Size: 1.2 GB

References

https://huggingface.co/reazon-research/japanese-wav2vec2-large-rs35kh

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC