Japanese HuBERT Large This is a mirror of japanese hubert large, originally released by rinna Co., Ltd. The original model is licensed under the Apache License 2.0. This mirror follows the same license terms. All copyrights remain with the original authors. Overview This is a Japanese HuBERT Large model trained by rinna Co., Ltd. Model summary The model architecture is the same as the original HuBERT Large model, which contains 24 transformer layers with 16 attention heads. The model was trained using code from the official repository, and the detailed training configuration can be found in the same repository and the original paper. Training The model was trained on approximately 19,000 hours of following Japanese speech corpus ReazonSpeech v1. ReazonSpeech Contributors Yukiya Hono Kentaro Mitsui Kei Sawada Release date March 7, 2024 How to use the model A fairseq checkpoint file can also be available here. How to cite References License The Apache 2.0 license
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy