Hindi asr_Wav2Vec2_xls_r_lm_300m_gpu TFWav2Vec2ForCTC from LegolasTheElf

Description

Pretrained Wav2vec2 pipeline, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_Wav2Vec2_xls_r_lm_300m is a Hindi model originally trained by LegolasTheElf.

NOTE: This pipeline only works on a CPU, if you need to use this pipeline on a GPU device please use pipeline_asr_Wav2Vec2_xls_r_lm_300m

Download Copy S3 URICopied!

How to use


pipeline = PretrainedPipeline('pipeline_asr_Wav2Vec2_xls_r_lm_300m_gpu', lang = 'hi')
annotations =  pipeline.transform(audioDF)
    

Model Information

Model Name: pipeline_asr_Wav2Vec2_xls_r_lm_300m_gpu
Type: pipeline
Compatibility: Spark NLP 4.2.0+
License: Open Source
Edition: Official
Language: hi
Size: 1.2 GB

Included Models

  • AudioAssembler
  • Wav2Vec2ForCTC