Description
Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_whisper_tiny_bulgarian_l_pipeline
is a Bulgarian model originally trained by nandovallec.
This model is only compatible with PySpark 3.4 and above
How to use
pipeline = PretrainedPipeline('asr_whisper_tiny_bulgarian_l_pipeline', lang = 'bg')
annotations = pipeline.transform(audioDF)
val pipeline = new PretrainedPipeline('asr_whisper_tiny_bulgarian_l_pipeline', lang = 'bg')
val annotations = pipeline.transform(audioDF)
Model Information
Model Name: | asr_whisper_tiny_bulgarian_l_pipeline |
Type: | pipeline |
Compatibility: | Spark NLP 5.1.4+ |
License: | Open Source |
Edition: | Official |
Language: | bg |
Size: | 390.9 MB |
References
https://huggingface.co/nandovallec/whisper-tiny-bg-l
Included Models
- AudioAssembler
- WhisperForCTC