search

RVC-Boss / GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
MIT License
35.72k stars 4.07k forks source link

使用macbookpro M1，一键三连报错 #352

Open zjsxr1979 opened 9 months ago

zjsxr1979 commented 9 months ago

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 file Traceback (most recent call last): File "/Users/shenxirong/01-workdata/00-sourcecode/GPT-SoVITS/webui.py", line 548, in open1abc with open(txt_path, "r",encoding="utf8") as f: FileNotFoundError: [Errno 2] No such file or directory: 'logs/laoLuo/2-name2text-0.txt'

------ 报错 "/Users/shenxirong/anaconda3/envs/GPTSoVits/bin/python3" GPT_SoVITS/prepare_datasets/1-get-text.py "/Users/shenxirong/anaconda3/envs/GPTSoVits/bin/python3" GPT_SoVITS/prepare_datasets/1-get-text.py Traceback (most recent call last): File "/Users/shenxirong/01-workdata/00-sourcecode/GPT-SoVITS/GPT_SoVITS/prepare_datasets/1-get-text.py", line 19, in from text.cleaner import clean_text File "/Users/shenxirong/01-workdata/00-sourcecode/GPT-SoVITS/GPT_SoVITS/text/cleaner.py", line 1, in from text import chinese, japanese, cleaned_text_to_sequence, symbols, english File "/Users/shenxirong/01-workdata/00-sourcecode/GPT-SoVITS/GPT_SoVITS/text/english.py", line 4, in from g2p_en import G2p File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/g2p_en/init.py", line 1, in from .g2p import G2p File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/g2p_en/g2p.py", line 22, in nltk.data.find('taggers/averaged_perceptron_tagger.zip') File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/nltk/data.py", line 542, in find return ZipFilePathPointer(p, zipentry) File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/nltk/compat.py", line 41, in _decorator return init_func(*args, kwargs) File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/nltk/data.py", line 394, in init zipfile = OpenOnDemandZipFile(os.path.abspath(zipfile)) File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/nltk/compat.py", line 41, in _decorator return init_func(*args, *kwargs) File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/nltk/data.py", line 935, in init zipfile.ZipFile.init(self, filename) File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/zipfile.py", line 1266, in init self._RealGetContents() 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 file Traceback (most recent call last): File "/Users/shenxirong/01-workdata/00-sourcecode/GPT-SoVITS/GPT_SoVITS/prepare_datasets/1-get-text.py", line 19, in from text.cleaner import clean_text File "/Users/shenxirong/01-workdata/00-sourcecode/GPT-SoVITS/GPT_SoVITS/text/cleaner.py", line 1, in from text import chinese, japanese, cleaned_text_to_sequence, symbols, english File "/Users/shenxirong/01-workdata/00-sourcecode/GPT-SoVITS/GPT_SoVITS/text/english.py", line 4, in from g2p_en import G2p File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/g2p_en/init.py", line 1, in from .g2p import G2p File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/g2p_en/g2p.py", line 22, in nltk.data.find('taggers/averaged_perceptron_tagger.zip') File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/nltk/data.py", line 542, in find return ZipFilePathPointer(p, zipentry) File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/nltk/compat.py", line 41, in _decorator return init_func(args, kwargs) File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/nltk/data.py", line 394, in init zipfile = OpenOnDemandZipFile(os.path.abspath(zipfile)) File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/nltk/compat.py", line 41, in _decorator return init_func(*args, **kwargs) File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/site-packages/nltk/data.py", line 935, in init zipfile.ZipFile.init(self, filename) File "/Users/shenxirong/anaconda3/envs/GPTSoVits/lib/python3.9/zipfile.py", line 1266, in init self._RealGetContents() 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 file Traceback (most recent call last): File "/Users/shenxirong/01-workdata/00-sourcecode/GPT-SoVITS/webui.py", line 548, in open1abc with open(txt_path, "r",encoding="utf8") as f: FileNotFoundError: [Errno 2] No such file or directory: 'logs/laoLuo/2-name2text-0.txt'

HyH-QAQ commented 9 months ago

加一，请问解决了吗

HyH-QAQ commented 9 months ago

你看一下自己的模型是不是放错了位置？

image

放到这个下面：GPT-SoVITS/GPT_SoVITS/pretrained_models 即是：/GPT_SoVITS/pretrained_models/chinese-hubert-base

tymon42 commented 9 months ago

预训练模型的位置放对了吗？

zjsxr1979 commented 9 months ago

你看一下自己的模型是不是放错了位置？ image 放到这个下面：GPT-SoVITS/GPT_SoVITS/pretrained_models 即是：/GPT_SoVITS/pretrained_models/chinese-hubert-base

我没放错啊，就是在项目GPT_SoVITS根目录下的GPT_SoVITS/pretrained_models 里面

截屏2024-02-02 22 54 25
tymon42 commented 9 months ago

还有个情况你也要检查下，这些模型的大小是不是100兆左右的大小（至少不能是若干 kb）

通过 某些途径下载的模型是个 alias 链接文件。

zjsxr1979 commented 9 months ago

预训练模型的位置放对了吗？

没错啊，就是在项目GPT_SoVITS根目录下的GPT_SoVITS/pretrained_models 里面，我还找了台windows试了下封装版，能跑，对比了windows版本的安装目录，没错啊

tymon42 commented 9 months ago

预训练模型的位置放对了吗？

没错啊，就是在项目GPT_SoVITS根目录下的GPT_SoVITS/pretrained_models 里面，我还找了台windows试了下封装版，能跑，对比了windows版本的安装目录，没错啊

那就不是 alias 文件的问题。

zjsxr1979 commented 9 months ago

还有个情况你也要检查下，这些模型的大小是不是100兆左右的大小（至少不能是若干 kb）

通过 某些途径下载的模型是个 alias 链接文件。

是的，都是100兆左右，对比了windows能跑的那个版本文件，大小完全一样

tymon42 commented 9 months ago

我的的 m2 直接拉取代码就行了，不用改代码。你改代码是遇到什么问题了吗？

zjsxr1979 commented 9 months ago

我的的 m2 直接拉取代码就行了，不用改代码。你该代码是遇到什么问题了吗？

我没改任何代码。。。

tymon42 commented 9 months ago

或者你可以把 WEB UI 的截图放上来，看看是不是路径没填对。

HyH-QAQ commented 9 months ago

用cpu训练：https://github.com/RVC-Boss/GPT-SoVITS/issues/290#issuecomment-1916306780

zjsxr1979 commented 9 months ago

或者你可以把 WEB UI 的截图放上来，看看是不是路径没填对。

截屏2024-02-02 23 21 48
zjsxr1979 commented 9 months ago

用cpu训练：#290 (comment)

试过了，都改成cpu了，问题依旧，没有任何变化，还是一样的报错

tymon42 commented 9 months ago

https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e/pgah3gvetrdy8ryt#W3oBn

我这些地方都是用绝对路径的，可以试试

或者你可以把 WEB UI 的截图放上来，看看是不是路径没填对。

截屏2024-02-02 23 21 48
ISDHN commented 9 months ago

似乎是nltk这个库的文件有问题，尝试卸载重装看看（？

Danny0802 commented 8 months ago

解决了吗？

mhkz commented 8 months ago

我的m1也是同样报错，但是没有解决

Lion-Wu commented 8 months ago

看起来是nltk的问题。用户文件夹中应该有一个nltk_data的文件夹，把它删掉重新运行试试，也有可能是网的问题，导致下载失败

projoy commented 6 months ago

我的是windows10，也遇到了这个问题，后来解决了。

问题过程如下： 1.最开始的时候机器上没有配置nltk_data，直接运行“一键三连”时，GPT-SoVITS会从github上拉取nltk。因为拉取的太慢，就手工停止了。 2.然后，手工安装了nltk，配置路径为d:/nltk_data 3.再运行“一键三连”时，就报了这个错误。

解决如下： 检查发现，在C:\Users\xxxx\AppData\Roaming\nltk_data这个路径下存在一个nltk_data目录，应该是第一次自动下载的不完整的数据。把C:\Users\xxxx\AppData\Roaming\nltk_data这个目录删除，使用d:/nltk_data。然后再重新运行服务，一切正常了

paulhahaha commented 6 months ago

解决了吗

gallonyin commented 3 months ago

我解决了，在本地下载一下两个文件（需要翻墙，本地开个vpn）。

使用python写个脚本下载： import nltk nltk.download('averaged_perceptron_tagger') nltk.download('cmudict')

然后可以在本地找到两个文件，我的电脑目录是： C:\Users\gallo\AppData\Roaming\nltk_data\taggers\averaged_perceptron_tagger.zip C:\Users\gallo\AppData\Roaming\nltk_data\corpora\cmudict.zip

把这两个文件拷贝到服务器上，我的服务器目录是： /root/nltk_data/taggers/averaged_perceptron_tagger.zip /root/nltk_data/corpora/cmudict.zip linux服务器的话 你可以先看下~/nltk_data 这个目录的位置。

然后这个报错就没了。

gallonyin commented 3 months ago

averaged_perceptron_tagger.zip cmudict.zip 文件直接发这里试试