udamaurizio/parler_Google_TTS_Ita_v1_prompted

该数据集是一个意大利语文本到语音（TTS）数据集，包含68个训练样本。数据集的特征包括文本、标准化转录、平均音高、音高标准差、信噪比、c50、语速、音素、噪声、混响、语音单调性和文本描述。数据集的总大小为28361字节，下载大小为18871字节。数据集的配置名为默认，数据文件路径为data/train-*。数据集的许可证为apache-2.0，标签为tts，大小类别为n<1K。

This dataset is an Italian text-to-speech (TTS) dataset containing 68 training samples. The features of the dataset include text, normalized transcription, mean pitch, pitch standard deviation, signal-to-noise ratio, c50, speaking rate, phonemes, noise, reverberation, speech monotony, and text description. The total size of the dataset is 28361 bytes, and the download size is 18871 bytes. The configuration name is default, and the data file path is data/train-*. The datasets license is apache-2.0, the tag is tts, and the size category is n<1K.