Ruoyi
Will fix the bugs in the later sft weights.
We recommend you to use Trump's voice as reference and directly generating voice with Chinese text.
please roll back to v1.4.3 to use the agent.
Hi, would you please add "cachetools" library into it? This will be helpful as we forgot to update the pyproject.toml. Please pin it to 5.3.1, thanks a lot for your...
执行构建agent代码的时候报错如下：Qwen2TokenizerFast has no attribute "get _token_id" . Did you mean:"sep_token_id"
use v1.4.3 for stable agent use.
In the later version, we plan to remove the fine-tune part. Instead, we'll add a series of tools to enhance your reference audio's quality.
> But what if I need to add a new language or a dialect that the model usually doesn't handle? We need to fine-tune the model to accomplish such a...
> Thanks a lot for your response, that's really helpful, I have one last question: does the data need to be cut to a certain length? I have multiple long...
The model has supported Italian in the latest version (v1.5) , you can find the weights here: https://huggingface.co/fishaudio/fish-speech-1.5
你可以参阅代码自行探索可能性