hugpadhugpad

facebook / wav2vec2-base-960h

Audio94M1.8M415Updated Nov 14, 2022
Hugging Face

Downloads

1.8M

Likes

415

Last updated

Nov 14, 2022

License

apache-2.0

The base model pretrained and fine-tuned on 960 hours of Librispeech on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz.

Tasks & library

  • automatic speech recognition
  • transformers

Tags

  • transformers
  • pytorch
  • tf
  • wav2vec2
  • audio
  • hf-asr-leaderboard

Technical specifications

Parameters94M
Librarytransformers
Languagesen
Licenseapache-2.0