Description
Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.test_pipeline is a Swedish model originally trained by marma.
How to use
pipeline = PretrainedPipeline("test_pipeline", lang = "sv")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("test_pipeline", lang = "sv")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | test_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | sv |
| Size: | 766.2 MB |
References
https://huggingface.co/marma/test
Included Models
- AudioAssembler
- Wav2Vec2ForCTC