Description
Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_whisper_small_thai_napatswift_pipeline
is a Thai model originally trained by napatswift.
This model is only compatible with PySpark 3.4 and above
How to use
pipeline = PretrainedPipeline('asr_whisper_small_thai_napatswift_pipeline', lang = 'th')
annotations = pipeline.transform(audioDF)
val pipeline = new PretrainedPipeline('asr_whisper_small_thai_napatswift_pipeline', lang = 'th')
val annotations = pipeline.transform(audioDF)
Model Information
Model Name: | asr_whisper_small_thai_napatswift_pipeline |
Type: | pipeline |
Compatibility: | Spark NLP 5.1.4+ |
License: | Open Source |
Edition: | Official |
Language: | th |
Size: | 1.7 GB |
References
https://huggingface.co/napatswift/whisper-small-thai
Included Models
- AudioAssembler
- WhisperForCTC