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
33.84k stars 3.88k forks source link

WAV格式文件出现：FileNotFoundError: [Errno 2] No such file or directory: 'logs/sibug/2-name2text-0.txt'报错 #480

Open HiSweetie opened 7 months ago

HiSweetie commented 7 months ago

Intel MacBook Pro(2019款) 16inch i7 9750 显卡：AMD Radeon Pro 5300M

系统版本为MacOS 12.7.3 (21H1015) 切片之后的文件均为.wav后缀 依次执行一键三连操作时，点按speech-to-text按钮时出现如下报错： LookupError:

Resource cmudict not found. Please use the NLTK Downloader to obtain the resource:

import nltk nltk.download('cmudict')

For more information see: https://www.nltk.org/data.html

Attempted to load corpora/cmudict

Searched in:

Traceback (most recent call last): File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/routes.py", line 442, in run_predict output = await app.get_blocks().process_api( File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/blocks.py", line 1389, in process_api result = await self.call_function( File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/blocks.py", line 1108, in call_function prediction = await utils.async_iteration(iterator) File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/utils.py", line 346, in async_iteration return await iterator.anext() File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/utils.py", line 339, in anext return await anyio.to_thread.run_sync( File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 2134, in run_sync_in_worker_thread return await future File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 851, in run result = context.run(func, args) File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/utils.py", line 322, in run_sync_iterator_async return next(iterator) File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/utils.py", line 691, in gen_wrapper yield from f(args, kwargs) File "/Users/mac_for_yu/Desktop/Software/AI_TTS/GPT-SoVITS-main3/webui.py", line 388, in open1a with open(txt_path, "r", encoding="utf8") as f: FileNotFoundError: [Errno 2] No such file or directory: 'logs/sibug/2-name2text-0.txt' "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/bin/python3" GPT_SoVITS/prepare_datasets/1-get-text.py "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/bin/python3" GPT_SoVITS/prepare_datasets/1-get-text.py Traceback (most recent call last): File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/routes.py", line 442, in run_predict output = await app.get_blocks().process_api( File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/blocks.py", line 1389, in process_api result = await self.call_function( File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/blocks.py", line 1108, in call_function prediction = await utils.async_iteration(iterator) File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/utils.py", line 346, in async_iteration return await iterator.anext() File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/utils.py", line 339, in anext return await anyio.to_thread.run_sync( File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 2134, in run_sync_in_worker_thread return await future File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 851, in run result = context.run(func, args) File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/utils.py", line 322, in run_sync_iterator_async return next(iterator) File "/Users/mac_for_yu/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/utils.py", line 691, in gen_wrapper yield from f(args, kwargs) File "/Users/mac_for_yu/Desktop/Software/AI_TTS/GPT-SoVITS-main3/webui.py", line 388, in open1a with open(txt_path, "r", encoding="utf8") as f: FileNotFoundError: [Errno 2] No such file or directory: 'logs/sibug/2-name2text-0.txt'

截屏2024-02-14 11 47 41

之前我在我的Windows电脑上使用一键整合包就没问题，但目前我主要是用Mac办公，希望懂行的朋友能帮忙解决一下这个问题。

Lion-Wu commented 7 months ago

创建一个python文件：

import nltk
nltk.download('cmudict')

然后运行它，会下载一个nltk文件。之后重新运行webui再试试 我运行的时候这个文件是会自动下载的，不知道怎么回事，有很多人没下载 另外这里有人与你相同的配置在GPT训练的时候显示没有GPU可训练，如果出现这个问题的话麻烦跟我说一声，我再看看

HiSweetie commented 7 months ago

谢谢。我想我已经解决了一键三连的那个问题，不过，正如你所料，我在进行GPT训练时提示：No supported gpu backend found!截屏2024-02-14 16 30 15

这样的话我在我的这台Mac上就只能先用CPU进行训练了吗？或者是我用我的Windows笔记本电脑训练完之后把训练好的模型拷贝到Mac上使用？这样可行吗？

Lion-Wu commented 7 months ago

看来估计是pytorch_lightning的问题，你可以先尝试把项目中GPT_SoVITS/s1_train.py中第112行中的gpu改成cpu看看应该能暂时解决问题

HiSweetie commented 7 months ago

我在进行SoVITS训练时还遇到了如下问题：

RuntimeError: MPS backend out of memory (MPS allocated: 6.64 GB, other allocations: 134.57 MB, max allowed: 6.77 GB). Tried to allocate 10.00 MB on private pool. Use PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 to disable upper limit for memory allocations (may cause system failure). 在Intel的Mac上，这个程序运行时貌似会占用大量的内存，不过我的Windows笔记本配置也不是最新的，Win本也是i7 9750的CPU，显卡是2070 8G显存，Windows和Mac同样都是16G的内存，但Windows上就没出现这样的情况。

Lion-Wu commented 7 months ago

MPS上已知是有内存泄漏的问题的，这个还没找到解决方法… 另外最近加了个DPO协同训练，使得训练显存翻倍了 所以用AMD显卡来训练可能比较难了吧

Lion-Wu commented 7 months ago

你试试降低batch size

ThreeManager785 commented 7 months ago

谢谢。我想我已经解决了一键三连的那个问题，不过，正如你所料，我在进行GPT训练时提示：No supported gpu backend found!截屏2024-02-14 16 30 15

这样的话我在我的这台Mac上就只能先用CPU进行训练了吗？或者是我用我的Windows笔记本电脑训练完之后把训练好的模型拷贝到Mac上使用？这样可行吗？

我以前忘记了怎么解决的这个问题，但是Mac肯定可以。我现在也在试图解决这个问题。

arctan90 commented 7 months ago

Same err came up to me. A brand new Win10 System. Resolved by downloading cmudict

> import nltk
> nltk.download('cmudict')

Suggesting add this step to Readme.MD. :D

创建一个python文件：

import nltk
nltk.download('cmudict')

然后运行它，会下载一个nltk文件。之后重新运行webui再试试 我运行的时候这个文件是会自动下载的，不知道怎么回事，有很多人没下载 另外这里有人与你相同的配置在GPT训练的时候显示没有GPU可训练，如果出现这个问题的话麻烦跟我说一声，我再看看

Lion-Wu commented 7 months ago

Same err came up to me. A brand new Win10 System. Resolved by downloading cmudict

> import nltk
> nltk.download('cmudict')

Suggesting add this step to Readme.MD. :D

创建一个python文件：

import nltk
nltk.download('cmudict')

然后运行它，会下载一个nltk文件。之后重新运行webui再试试 我运行的时候这个文件是会自动下载的，不知道怎么回事，有很多人没下载 另外这里有人与你相同的配置在GPT训练的时候显示没有GPU可训练，如果出现这个问题的话麻烦跟我说一声，我再看看

I think it might be caused by poor network connection, because the file will be downloaded automatically when running the project for the first time.

xiaolongww commented 6 months ago

可以通过这种方式查看是否有nltk： import nltk print("nltk data path:", nltk.data.path)

通过这种方式，我知道了在C:\Users\Administrator\AppData\Roaming\ntlk_data有这部分数据；而且当另一台计算机出现Resource cmudict not found.Please use the NLTK Downloader to obtain the resource: 时，我直接把这个文件夹的数据拷过去即可 image