Skip to content

Transformer - LibriVox + Decoding/Rescoring

FacebookSpeech recognition (ASR)Open weights

Transformer - LibriVox + Decoding/Rescoring is Speech recognition (ASR) model published by Facebook in 2019 featuring 296000000.0 parameters.

About Transformer - LibriVox + Decoding/Rescoring

We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functions. We perform experiments on the standard LibriSpeech dataset, and le

Details

Provider
Facebook
Task
Speech recognition (ASR)
Parameters
296000000.0
Released
2019-11-19
Open weights
Yes
View model source

Explore

FAQ