Description
Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bengali_whisper_base_pipeline is a Bengali model originally trained by emon-j.
How to use
pipeline = PretrainedPipeline("bengali_whisper_base_pipeline", lang = "bn")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("bengali_whisper_base_pipeline", lang = "bn")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | bengali_whisper_base_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | bn |
| Size: | 642.0 MB |
References
https://huggingface.co/emon-j/Bengali-Whisper-Base
Included Models
- AudioAssembler
- WhisperForCTC