Edit on GitHub
  • John Snow Labs
  • Mar 11, 2023

Tamil asr_Tamil_Wav2Vec_xls_r_300m_Tamil_colab TFWav2Vec2ForCTC from bharat-raghunathan

  • wav2vec2
  • ta
  • audio
  • open_source
  • pipeline
  • asr

Description

Pretrained Wav2vec2 pipeline, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_Tamil_Wav2Vec_xls_r_300m_Tamil_colab is a Tamil model originally trained by bharat-raghunathan.

NOTE: This pipeline only works on a CPU, if you need to use this pipeline on a GPU device please use pipeline_asr_Tamil_Wav2Vec_xls_r_300m_Tamil_colab_gpu

Download Copy S3 URI

How to use


    pipeline = PretrainedPipeline('pipeline_asr_Tamil_Wav2Vec_xls_r_300m_Tamil_colab', lang = 'ta')
    annotations =  pipeline.transform(audioDF)
    


    val pipeline = new PretrainedPipeline("pipeline_asr_Tamil_Wav2Vec_xls_r_300m_Tamil_colab", lang = "ta")
    val annotations = pipeline.transform(audioDF)

Model Information

Model Name: pipeline_asr_Tamil_Wav2Vec_xls_r_300m_Tamil_colab
Type: pipeline
Compatibility: Spark NLP 4.4.0+
License: Open Source
Edition: Official
Language: ta
Size: 1.2 GB

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC