Description
Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.whisper_medium_korean_v0_1_2_pipeline is a Korean model originally trained by morish.
How to use
pipeline = PretrainedPipeline("whisper_medium_korean_v0_1_2_pipeline", lang = "ko")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("whisper_medium_korean_v0_1_2_pipeline", lang = "ko")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | whisper_medium_korean_v0_1_2_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ko |
| Size: | 4.8 GB |
References
https://huggingface.co/morish/whisper-medium-ko-v0_1_2
Included Models
- AudioAssembler
- WhisperForCTC