darshanmakwana/music_genre_tokenized
收藏Hugging Face2024-07-16 更新2024-07-22 收录
下载链接：
https://hf-mirror.com/datasets/darshanmakwana/music_genre_tokenized
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含使用SemantiCodec进行标记化的音频数据，用于进行AR音乐生成的实验。数据集来源于[lewtun/music_genres](https://huggingface.co/datasets/lewtun/music_genres)，并提供了用于标记化的Python脚本。
This dataset contains tokenized audio from lewtun/music_genres using SemantiCodec for performing experiments on AR music generation. The dataset includes four features: audio_tokens (sequence of audio tokens), genre_id (genre ID), genre (genre), and song_id (song ID). It is divided into a training set with 19909 examples and a test set with 5076 examples. The download size of the dataset is 123311267 bytes, and the total size is 601934148 bytes.
提供机构：
darshanmakwana
