aether-raid/atc-tts-voxtream

## ATC TTS Voxtream Dataset This dataset is prepared for training the Voxtream TTS model and follows the format of [herimor/voxtream-train-9k](https://huggingface.co/datasets/herimor/voxtream-train-9k). **Source:** Based on the Singaporean SG Eleven dataset: [aether-raid/sg-aviation-el-combined](https://huggingface.co/datasets/aether-raid/sg-aviation-el-combined) **Description:** - All features are provided as single batched `.npy` files: - `mimi_codes_16cb.npy`: Mimi codec tokens (16 codebooks) - `phone_emb_indices.npy`: Alignment of phoneme tokens to Mimi frames - `phone_tokens.npy`: Phoneme tokens - `sem_label_shifts.npy`: Monotonic phoneme alignment labels - `spk_templates.npy`: Speaker templates (first 3 seconds, if available) - `uids.npy` contains the list of utterance IDs, matching the batch dimension of all features. **Usage:** See [herimor/voxtream-train-9k](https://huggingface.co/datasets/herimor/voxtream-train-9k) for loading and training examples. **License:** See original dataset for licensing and usage restrictions.空中交通管制语音合成（Air Traffic Control, ATC）Voxtream 数据集 本数据集专为训练Voxtream文本到语音（Text-to-Speech, TTS）模型打造，且严格遵循[herimor/voxtream-train-9k](https://huggingface.co/datasets/herimor/voxtream-train-9k)的数据集格式规范。 **数据源：** 本数据集基于新加坡SG Eleven数据集构建，原始数据源为[aether-raid/sg-aviation-el-combined](https://huggingface.co/datasets/aether-raid/sg-aviation-el-combined)。 **数据集说明：** - 所有特征均以单批次.npy文件格式提供： - `mimi_codes_16cb.npy`：Mimi编解码器（Mimi codec）Token（16个码本） - `phone_emb_indices.npy`：音素Token与Mimi帧的对齐索引 - `phone_tokens.npy`：音素Token - `sem_label_shifts.npy`：单调音素对齐标签 - `spk_templates.npy`：说话人模板（若可用则取音频前3秒片段） - `uids.npy` 存储话语ID列表，其维度与所有特征的批次维度保持一致。 **使用方法：** 如需了解数据加载与训练的具体示例，请参考[herimor/voxtream-train-9k](https://huggingface.co/datasets/herimor/voxtream-train-9k)。 **授权协议：** 有关数据集的授权条款及使用限制，请参阅原始数据集的相关说明。