About

The goal of this project is to train a speech recognition model for audio to the International Phonetic Alphabet for American English. It is based on Multipa and Wav2vec2 model architecture trained on the LibriSpeech dataset.

The project is currently a work in progress.

Downloads last month
377
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train ginic/wav2vec-large-xlsr-en-ipa