utils/models.yaml

# models that generate text from audio data.
wav2vec:
  task: text_to_speech
  url: https://huggingface.co/facebook/wav2vec2-base-960h

wav2vec2:
  task: text_to_speech
  url: https://huggingface.co/yongjian/wav2vec2-large-a

whisper_tiny:
  task: text_to_speech
  url: https://huggingface.co/openai/whisper-tiny
  description: "this is the smallest whisper model that will be used for cloud deployment"
  year: 2022

whisper_base:
  task: text_to_speech
  url: https://huggingface.co/openai/whisper-base
  year: 2022

whisper_medium:
  task: text_to_speech
  url: https://huggingface.co/openai/whisper-medium
  year: 2022

bart_large:
  task: text_to_summary
  url: https://huggingface.co/facebook/bart-large-cnn
  year: 2022