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)
用的macbookpro M1，一键三连报错，已经根据yoko-penta的解决方案：https://github.com/RVC-Boss/GPT-SoVITS/issues/270 把 GPT-SoVITS\GPT_SoVITS\prepare_datasets目录下的三个.py文件的 os.environ["CUDA_VISIBLE_DEVICES"]= os.environ.get("_CUDA_VISIBLE_DEVICES") 全部换成： os.environ["CUDA_VISIBLE_DEVICES"] = "0"， 还是不行，总是报： File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/zipfile.py", line 1333, in _RealGetContents raise BadZipFile("File is not a zip file") zipfile.BadZipFile: File is not a zip...
都是按照教程装的环境，在一键三连的时候出现的问题，看上去是包的问题，搜了一会儿还是没有成功解决 import _jieba_fast_functions_py3 as _jieba_fast_functions ImportError: dlopen(/Users/czy/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/_jieba_fast_functions_py3.cpython-39-darwin.so, 0x0002): tried: '/Users/czy/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/_jieba_fast_functions_py3.cpython-39-darwin.so' (mach-o file, but is an incompatible architecture (have 'x86_64', need 'arm64')), '/System/Volumes/Preboot/Cryptexes/OS/Users/czy/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/_jieba_fast_functions_py3.cpython-39-darwin.so' (no such file), '/Users/czy/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/_jieba_fast_functions_py3.cpython-39-darwin.so' (mach-o file, but is...
Seed set to 1234 Using 16bit Automatic Mixed Precision (AMP) GPU available: True (cuda), used: True TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU...
以下是我的运行日志： Z:\GPT-SoVITS-beta>runtime\python.exe webui.py Running on local URL: http://0.0.0.0:9874 "Z:\GPT-SoVITS-beta\runtime\python.exe" GPT_SoVITS/s2_train.py --config "Z:\GPT-SoVITS-beta\TEMP/tmp_s2.json" "Z:\GPT-SoVITS-beta\runtime\python.exe" GPT_SoVITS/s1_train.py --config_file "Z:\GPT-SoVITS-beta\TEMP/tmp_s1.yaml" Seed set to 1234 Using 16bit Automatic Mixed Precision (AMP) GPU available: True (cuda),...
"E:\GPT-SoVITS-beta\runtime\python.exe" GPT_SoVITS/prepare_datasets/1-get-text.py "E:\GPT-SoVITS-beta\runtime\python.exe" GPT_SoVITS/prepare_datasets/1-get-text.py 一直这样，不动地方。我看教程要清空之前切割的音频文件是吗？我怎么感觉不对劲。
我使用的是 HP3_all_vocals， HP2 我也试了，也有类似的问题，见图片 确认原始音频中是没有削波的，原始音频在这里 链接: https://pan.baidu.com/s/1JId3C6qJbtwKcD8z2oFnUw 提取码: rg98
如题 也尝试了不同的音频但是同样的错误
