Description
Pretrained Wav2vec2 pipeline, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_exp_w2v2t_xls_r_s438 is a German model originally trained by jonatasgrosman.
NOTE: This pipeline only works on a CPU, if you need to use this pipeline on a GPU device please use pipeline_asr_exp_w2v2t_xls_r_s438
How to use
pipeline = PretrainedPipeline('pipeline_asr_exp_w2v2t_xls_r_s438_gpu', lang = 'de')
annotations = pipeline.transform(audioDF)
val pipeline = new PretrainedPipeline("pipeline_asr_exp_w2v2t_xls_r_s438_gpu", lang = "de")
val annotations = pipeline.transform(audioDF)
Model Information
| Model Name: | pipeline_asr_exp_w2v2t_xls_r_s438_gpu |
| Type: | pipeline |
| Compatibility: | Spark NLP 4.2.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | de |
| Size: | 1.2 GB |
Included Models
- AudioAssembler
- Wav2Vec2ForCTC