Edit on GitHub
  • John Snow Labs
  • Sep 03, 2024

Chinese whisper_tiny_chinese_twi_baseline_pipeline pipeline WhisperForCTC from xmzhu

  • zh
  • open_source
  • pipeline
  • onnx

Description

Pretrained WhisperForCTC, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.whisper_tiny_chinese_twi_baseline_pipeline is a Chinese model originally trained by xmzhu.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("whisper_tiny_chinese_twi_baseline_pipeline", lang = "zh")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("whisper_tiny_chinese_twi_baseline_pipeline", lang = "zh")
val annotations = pipeline.transform(df)

Model Information

Model Name: whisper_tiny_chinese_twi_baseline_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: zh
Size: 390.7 MB

References

https://huggingface.co/xmzhu/whisper-tiny-zh-TW-baseline

Included Models

  • AudioAssembler
  • WhisperForCTC