thenewsupercell/V1_finetuned_audio_embeddings_celeb-df-dataset

该数据集包含音频文件及其相关描述信息，如来源(source)、目标(target1, target2)、方法(method)、分类(category)、类型(type)、种族(race)、性别(gender)等。此外，还包括文本(text)和音频的向量表示(audio_embeddings)。数据集分为训练集、验证集和测试集三个部分。

The dataset includes audio files and their associated descriptive information, such as source, target1, target2, method, category, type, race, gender, etc. It also includes text and vector representations of the audio (audio_embeddings). The dataset is divided into three parts: training set, validation set, and test set.