Description
Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.whisper_medium_ga2en_v5_2_1_r_pipeline is a Irish model originally trained by ymoslem.
How to use
pipeline = PretrainedPipeline("whisper_medium_ga2en_v5_2_1_r_pipeline", lang = "ga")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("whisper_medium_ga2en_v5_2_1_r_pipeline", lang = "ga")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | whisper_medium_ga2en_v5_2_1_r_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ga |
| Size: | 4.8 GB |
References
https://huggingface.co/ymoslem/whisper-medium-ga2en-v5.2.1-r
Included Models
- AudioAssembler
- WhisperForCTC