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

Turkish wav2vec2_base_760_turkish_pipeline pipeline Wav2Vec2ForCTC from ceyda

  • tr
  • open_source
  • pipeline
  • onnx

Description

Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.wav2vec2_base_760_turkish_pipeline is a Turkish model originally trained by ceyda.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("wav2vec2_base_760_turkish_pipeline", lang = "tr")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("wav2vec2_base_760_turkish_pipeline", lang = "tr")
val annotations = pipeline.transform(df)

Model Information

Model Name: wav2vec2_base_760_turkish_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: tr
Size: 232.8 MB

References

https://huggingface.co/ceyda/wav2vec2-base-760-turkish

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC