Description
Pretrained Hubert pipeline, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_swin_exp_w2v2t_fr_hubert_s990
is a French model originally trained by jonatasgrosman.
How to use
pipeline = PretrainedPipeline('pipeline_asr_swin_exp_w2v2t_fr_hubert_s990', lang = 'fr')
annotations = pipeline.transform(audioDF)
val pipeline = new PretrainedPipeline("pipeline_asr_swin_exp_w2v2t_fr_hubert_s990", lang = "fr")
val annotations = pipeline.transform(audioDF)
Model Information
Model Name: | pipeline_asr_swin_exp_w2v2t_fr_hubert_s990 |
Type: | pipeline |
Compatibility: | Spark NLP 4.4.0+ |
License: | Open Source |
Edition: | Official |
Language: | fr |
Size: | 2.4 GB |
Included Models
- AudioAssembler
- HubertForCTC