Description
Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.malaysian_whisper_medium_pipeline is a Malay (macrolanguage) model originally trained by mesolitica.
How to use
pipeline = PretrainedPipeline("malaysian_whisper_medium_pipeline", lang = "ms")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("malaysian_whisper_medium_pipeline", lang = "ms")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | malaysian_whisper_medium_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ms |
| Size: | 2.4 GB |
References
https://huggingface.co/mesolitica/malaysian-whisper-medium
Included Models
- AudioAssembler
- WhisperForCTC