waynecraig/fish-speech-1.5-wuhan

Fish Speech 1.5 - Wuhan Dialect

English | 中文

English

This is a finetuned version of Fish Speech 1.5 specifically optimized for Wuhan dialect (武汉话). The model has been trained on 26.75 hours of high-quality Wuhan dialect speech data.

Model Details

• Base Model: Fish Speech 1.5
• Training Data: 26.75 hours of Wuhan dialect speech
• Language: Chinese (Wuhan Dialect)
• License: CC-BY-NC-SA-4.0 (inherited from base model)

Audio Samples

Sample	Description	Input Text	Audio
Sample 1	Basic greeting in Wuhan dialect	你在搞么斯？一起去吃羊肉串么？	1.wav
Sample 2	Daily conversation in Wuhan dialect	我家伢这个周末都没出门，他说他要的家里读书。	2.wav

Usage

This model follows the same usage pattern as the original Fish Speech model. Please refer to the official repository for detailed setup and usage instructions.

Important Note: When following the official instructions, make sure to replace the original model path with this model's path (fish-speech-1.5-wuhan).

Citation

If you use this model, please cite both the original Fish Speech paper and this finetuned version:

@misc{fish-speech-v1.4,
      title={Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis}, 
      author={Shijia Liao and Yuxuan Wang and Tianyu Li and Yifan Cheng and Ruoyi Zhang and Rongzhi Zhou and Yijin Xing},
      year={2024},
      eprint={2411.01156},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2411.01156}, 
}

---

Chinese

这是基于 Fish Speech 1.5 微调的武汉话语音合成模型。该模型使用26.75小时的高质量武汉话语音数据训练而成。

模型详情

• 基础模型: Fish Speech 1.5
• 训练数据: 26.75小时武汉话语音
• 语言: 中文（武汉方言）
• 许可证: CC-BY-NC-SA-4.0（继承自基础模型）

音频示例

示例	描述	输入文本	音频
示例 1	武汉话基本问候语	你在搞么斯？一起去吃羊肉串么？	1.wav
示例 2	武汉话日常对话	我家伢这个周末都没出门，他说他要的家里读书。	2.wav

使用方法

本模型的使用方式与原始 Fish Speech 模型相同。请参考官方仓库获取详细的设置和使用说明。

重要提示：在按照官方说明操作时，请确保将原始模型路径替换为本模型的路径（fish-speech-1.5-wuhan）。

引用

如果您使用本模型，请同时引用原始Fish Speech论文和本微调版本：

@misc{fish-speech-v1.4,
      title={Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis}, 
      author={Shijia Liao and Yuxuan Wang and Tianyu Li and Yifan Cheng and Ruoyi Zhang and Rongzhi Zhou and Yijin Xing},
      year={2024},
      eprint={2411.01156},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2411.01156}, 
}