Description
Pretrained Wav2vec2 pipeline, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_xlsr_53_wav2vec is a Hindi model originally trained by harshit345.
NOTE: This pipeline only works on a CPU, if you need to use this pipeline on a GPU device please use pipeline_asr_xlsr_53_wav2vec_gpu
How to use
pipeline = PretrainedPipeline('pipeline_asr_xlsr_53_wav2vec', lang = 'hi')
annotations = pipeline.transform(audioDF)
val pipeline = new PretrainedPipeline("pipeline_asr_xlsr_53_wav2vec", lang = "hi")
val annotations = pipeline.transform(audioDF)
Model Information
| Model Name: | pipeline_asr_xlsr_53_wav2vec |
| Type: | pipeline |
| Compatibility: | Spark NLP 4.4.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | hi |
| Size: | 1.2 GB |
Included Models
- AudioAssembler
- Wav2Vec2ForCTC