Fine Tune Wav2Vec Bert 2.0 for Jyutping Recogition This repository contains the code for fine tuning the Wav2Vec Bert 2.0 model on the Common Voice 17 Cantonese dataset for Jyutping recognition. The model is trained on the Common Voice 17 Cantonese dataset. Inference Please clone the repo and follow the instructions to run the inference.
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy