Edit on GitHub
  • John Snow Labs
  • Apr 03, 2025

Chinese mandarin_wav2vec2_aishell1_pipeline pipeline Wav2Vec2ForCTC from kehanlu

  • zh
  • open_source
  • pipeline
  • onnx

Description

Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.mandarin_wav2vec2_aishell1_pipeline is a Chinese model originally trained by kehanlu.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("mandarin_wav2vec2_aishell1_pipeline", lang = "zh")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("mandarin_wav2vec2_aishell1_pipeline", lang = "zh")
val annotations = pipeline.transform(df)

Model Information

Model Name: mandarin_wav2vec2_aishell1_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: zh
Size: 359.3 MB

References

https://huggingface.co/kehanlu/mandarin-wav2vec2-aishell1

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC