RXS
RXS
Hello, I try to # convert the 7B model to ggml FP16 format but I found a problem? Is that because of the model problem? 🙏🏻 ```zsh python3 convert-pth-to-ggml.py models/7B/...
本教程已过时，请参照Lion-Wu的教程，目前已经支持MPS训练和推理： https://github.com/RVC-Boss/GPT-SoVITS/issues/93#issuecomment-1905782184 Mac 训练比较困难，mps训练目前没测试成功，本地推理和预处理是可以的,效果挺不错，(稍微有吞字问题),感谢作者开源！ ## 推理 文件可以在Colab或者云服务商上训练然后把模型下载下来 整合包参考：https://github.com/RVC-Boss/GPT-SoVITS/issues/4 ### 1.首先需要先把webui跑起来 ```bash python web.py ``` ### 2.点Allow到浏览器打开 ### 3. 选好GPT模型和SOVITS 模型 点击是否开启TTS推理WebUI 这个时候可能会报错，需要修改GPT_SoVITS/inference_webui.py用CPU推理 ### 4. 需要改两个地方 1. 把CUDA改成CPU 2. 把半精度改成全精度 model.half()...
想请问一下现在支持英文数据集的微调和推理了吗？ 看README支持了English dataset fine tune training.
### 使用的 Butterfly 版本？ | What version of Butterfly are you use? 4.12 ### 是否修改过主题文件？ || Has the theme files been modified? 是 (Yes) ### 使用的瀏覽器？ || What browse are...
## 4. Train the model on CPU and MPS device (GPU) Hello, I think This part "model": model.__class__.__name__, # Add a comma here, need to add a comma. ``` #...
添加评论限高选项
1.6.35版本更新后新增的评论内容的限高似乎导致出现多余折叠按钮，并没有折叠具体内容。希望添加是否开启评论限高选项，谢谢 
https://github.com/RoversX/nvidia_fan_control_linux Example output ```bash x@x:~$ ./fan.sh [sudo] password for x: ============================================================ Driver Version: 535.183.01 GPU 0: NVIDIA GeForce RTX 2080 Ti Fan Count: 1 ============================================================ Temperature: 42°C Total Curve Point:...
### Check List - [X] I have already read README. - [X] I have already searched existing issues. - [X] I have already searched existing pull requrests. ### Feature Request...