whisper-ner-v1 / README.md
aiola's picture
Update readme
03f6039 verified
|
raw
history blame
773 Bytes
metadata
license: mit
datasets:
  - numind/NuNER
language:
  - en
pipeline_tag: zero-shot-classification
tags:
  - asr
  - Automatic Speech Recognition
  - Whisper
  - Ner
  - Named entity recognition

Whisper Ner

Whisper ner is an advanced model that allows joint speech transcription and entity recognition. WhisperNER supports open-type NER, enabling recognition of diverse and evolving entities at inference. We augment a large synthetic dataset with synthetic speech samples. This allows us to train WhisperNER on a large number of examples with diverse NER tags. During training, the model is prompted with NER labels and optimized to output the transcribed utterance along with the corresponding tagged entities.


Training Details


Usage