Aybee5/hausa-tts-small

Mimic Studio Hausa TTS 数据集是一个用于训练文本到语音模型的音频数据集，包含62个样本，语言为豪萨语，由两位演讲者Surajo Nuhu Umar和Umar Musa Halliru录制。数据集格式兼容Unsloth TTS模型，音频格式为24kHz采样率的WAV文件。数据集结构包括元数据文件和音频文件，适用于Unsloth TTS模型的训练。

The Mimic Studio Hausa TTS Dataset is an audio dataset for training text-to-speech models, containing 62 samples in the Hausa language, recorded by two speakers, Surajo Nuhu Umar and Umar Musa Halliru. The dataset format is compatible with Unsloth TTS models, and the audio format is WAV files with a sampling rate of 24kHz. The dataset structure includes metadata and audio files, suitable for training with Unsloth TTS models.