Description
Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.wav2vec2_bengali_300m_pipeline is a Bengali model originally trained by Tahsin-Mayeesha.
How to use
pipeline = PretrainedPipeline("wav2vec2_bengali_300m_pipeline", lang = "bn")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("wav2vec2_bengali_300m_pipeline", lang = "bn")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | wav2vec2_bengali_300m_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | bn |
| Size: | 1.2 GB |
References
https://huggingface.co/Tahsin-Mayeesha/wav2vec2-bn-300m
Included Models
- AudioAssembler
- Wav2Vec2ForCTC