Edit on GitHub
  • John Snow Labs
  • Apr 02, 2025

Quechua wav2vec2_xlsr_300m_quechua_pipeline pipeline Wav2Vec2ForCTC from ivangtorre

  • qu
  • open_source
  • pipeline
  • onnx

Description

Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.wav2vec2_xlsr_300m_quechua_pipeline is a Quechua model originally trained by ivangtorre.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("wav2vec2_xlsr_300m_quechua_pipeline", lang = "qu")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("wav2vec2_xlsr_300m_quechua_pipeline", lang = "qu")
val annotations = pipeline.transform(df)

Model Information

Model Name: wav2vec2_xlsr_300m_quechua_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: qu
Size: 766.4 MB

References

https://huggingface.co/ivangtorre/wav2vec2-xlsr-300m-quechua

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC