GPT-SoVITS
GPT-SoVITS copied to clipboard
RVC-Boss
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
retrain the base models: huberts, roberta, etc from scratch with other languages?
一键三连中途报错
已经做好了切割、标注，点击一键三连时报错，显示没有'logs/xxx/2-name2text-0.txt'，但是整个logs文件夹都是他自己生成的啊，我手动创建一个文件，在运行的时候就自己删除了，运行一键三连的终端输出如下： "/Users/mac/anaconda3/envs/GPTSoVits/bin/python" GPT_SoVITS/prepare_datasets/1-get-text.py "/Users/mac/anaconda3/envs/GPTSoVits/bin/python" GPT_SoVITS/prepare_datasets/1-get-text.py Traceback (most recent call last): Traceback (most recent call last): File "/Users/mac/Desktop/GPT-SoVITS/GPT_SoVITS/prepare_datasets/1-get-text.py", line 56, in File "/Users/mac/Desktop/GPT-SoVITS/GPT_SoVITS/prepare_datasets/1-get-text.py", line 56, in tokenizer = AutoTokenizer.from_pretrained(bert_pretrained_dir) tokenizer =...
**系统:** M1 Pro **问题:** 无法调用 mps，自动回退 CPU 处理 **警告:** 
### 开启SoVITE训练失败 *错误信息* ```bash RuntimeError: Unsupported type byte size: ComplexFloat ```
Excellent project and much appreciated. My question is described in title. I just want to run a simply script to run inference instead of using WebUI, anyone knows how?
 
我用自己微调的模型，去推理目标文字时，发现会有一些小片段会不读或者重复读的情况；觉得是不是微调有问题，后面直接用基准模型去推理，发现也是一样的。有人有碰到类似问题吗，哪里可以寻找其他基准模型？
Hi I'm trying to use a sample to train and inference a text. I got some output in the older version, but after updating to the latest version, it creates...
``` Downloading: "https://github.com/r9y9/open_jtalk/releases/download/v1.11.1/open_jtalk_dic_utf_8-1.11.tar.gz" dic.tar.gz: 0.00B [00:00, ?B/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can...
