Edit on GitHub
  • John Snow Labs
  • Apr 06, 2025

Moldavian, Moldovan, Romanian wav2vec2_base_10k_voxpopuli_ft_romanian_pipeline pipeline Wav2Vec2ForCTC from facebook

  • ro
  • open_source
  • pipeline
  • onnx

Description

Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.wav2vec2_base_10k_voxpopuli_ft_romanian_pipeline is a Moldavian, Moldovan, Romanian model originally trained by facebook.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("wav2vec2_base_10k_voxpopuli_ft_romanian_pipeline", lang = "ro")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("wav2vec2_base_10k_voxpopuli_ft_romanian_pipeline", lang = "ro")
val annotations = pipeline.transform(df)

Model Information

Model Name: wav2vec2_base_10k_voxpopuli_ft_romanian_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: ro
Size: 233.8 MB

References

https://huggingface.co/facebook/wav2vec2-base-10k-voxpopuli-ft-ro

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC