Description
Pretrained Wav2Vec2ForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.xlsr_wav2vec2_arabic_pipeline is a Arabic model originally trained by Abosteet.
How to use
pipeline = PretrainedPipeline("xlsr_wav2vec2_arabic_pipeline", lang = "ar")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("xlsr_wav2vec2_arabic_pipeline", lang = "ar")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | xlsr_wav2vec2_arabic_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ar |
| Size: | 1.2 GB |
References
https://huggingface.co/Abosteet/XLSR-Wav2Vec2-arabic
Included Models
- AudioAssembler
- Wav2Vec2ForCTC