Description
Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.common_voice_lithuanian_fairseq_pipeline is a Lithuanian model originally trained by birgermoell.
How to use
pipeline = PretrainedPipeline("common_voice_lithuanian_fairseq_pipeline", lang = "lt")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("common_voice_lithuanian_fairseq_pipeline", lang = "lt")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | common_voice_lithuanian_fairseq_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | lt |
| Size: | 233.7 MB |
References
https://huggingface.co/birgermoell/common-voice-lithuanian-fairseq
Included Models
- AudioAssembler
- Wav2Vec2ForCTC