Central Khmer, Khmer asr_wav2vec2_xlsr_khmer TFWav2Vec2ForCTC from gagan3012

Description

Pretrained Wav2vec2 pipeline, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_wav2vec2_xlsr_khmer is a Central Khmer, Khmer model originally trained by gagan3012.

NOTE: This pipeline only works on a CPU, if you need to use this pipeline on a GPU device please use pipeline_asr_wav2vec2_xlsr_khmer_gpu

Download Copy S3 URI

How to use


    pipeline = PretrainedPipeline('pipeline_asr_wav2vec2_xlsr_khmer', lang = 'km')
    annotations =  pipeline.transform(audioDF)
    

    val pipeline = new PretrainedPipeline("pipeline_asr_wav2vec2_xlsr_khmer", lang = "km")
    val annotations = pipeline.transform(audioDF)
    

Model Information

Model Name: pipeline_asr_wav2vec2_xlsr_khmer
Type: pipeline
Compatibility: Spark NLP 4.4.0+
License: Open Source
Edition: Official
Language: km
Size: 1.2 GB

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC