请问如下报错如何解决？ about vits_with_chatgpt-gpt3 HOT 8 CLOSED

BV13t4y1V7DV，cmake安装成功后，直接pip install -r requirements.txt,应该能避免环境冲突问题。或者直接用封装版的Japanese cleaner

from vits_with_chatgpt-gpt3.

感谢 已解决环境冲突 但我在使用封装版的Japanese cleaner完成text文件夹和cleaners压缩包解压替换后 仍出现如下错误 请问原因是？
Traceback (most recent call last):
File "D:...\vits_with_chatgpt-gpt3\main.py", line 6, in
from text import text_to_sequence
File "D:...\vits_with_chatgpt-gpt3\text_init_.py", line 2, in
from text import cleaners
File "D:...\vits_with_chatgpt-gpt3\text\cleaners.py", line 3, in
from text.japanese import clean_japanese, japanese_to_romaji_with_accent, japanese_to_ipa, japanese_to_ipa2, japanese_to_ipa3
File "D:...\vits_with_chatgpt-gpt3\text\japanese.py", line 6, in
dll = ctypes.cdll.LoadLibrary('cleaners/JapaneseCleaner.dll')
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.2800.0_x64__qbz5n2kfra8p0\lib\ctypes_init_.py", line 452, in LoadLibrary
return self.dlltype(name)
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.2800.0_x64__qbz5n2kfra8p0\lib\ctypes_init.py", line 374, in init
self._handle = _dlopen(self._name, mode)
FileNotFoundError: Could not find module 'D:\Program Files (x86)\IDE\apps\PyCharm-P\ch-0\231.8109.197\jbr\bin\cleaners\JapaneseCleaner.dll' (or one of its dependencies). Try using the full path with constructor syntax.

from vits_with_chatgpt-gpt3.

Japanese cleaners解压后应该是一个cleaners文件夹，里面有 char.bin、JapaneseCleaner.dll、matrix.bin、sys.dic、unk.dic。你看看现在是把这个文件夹放在哪个位置，试一下直接放在你显示的这个路径"D:\Program Files (x86)\IDE\apps\PyCharm-P\ch-0\231.8109.197\jbr\bin\cleaners"

from vits_with_chatgpt-gpt3.

十分感谢 现在项目后端已经能运行起来了
但在结合前端使用的时候却只能提供空回答 并报如下错误 请问是什么原因呢
ERROR:local_chat:Exception on /chat [GET]
Traceback (most recent call last):
File "D:\EmiyaKatuz\CS_Homework\vits_with_chatgpt-gpt3\venv\lib\site-packages\flask\app.py", line 2528, in wsgi_app
response = self.full_dispatch_request()
File "D:\EmiyaKatuz\CS_Homework\vits_with_chatgpt-gpt3\venv\lib\site-packages\flask\app.py", line 1825, in full_dispatch_request
rv = self.handle_user_exception(e)
File "D:\EmiyaKatuz\CS_Homework\vits_with_chatgpt-gpt3\venv\lib\site-packages\flask\app.py", line 1823, in full_dispatch_request
rv = self.dispatch_request()
File "D:\EmiyaKatuz\CS_Homework\vits_with_chatgpt-gpt3\venv\lib\site-packages\flask\app.py", line 1799, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
File "D:\EmiyaKatuz\CS_Homework\vits_with_chatgpt-gpt3\local_chat.py", line 103, in text_api
response, new_history = model.chat(tokenizer, message, history)
File "D:\EmiyaKatuz\CS_Homework\vits_with_chatgpt-gpt3\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\19110/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py", line 1255, in chat
outputs = self.generate(**inputs, **gen_kwargs)
File "D:\EmiyaKatuz\CS_Homework\vits_with_chatgpt-gpt3\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "D:\EmiyaKatuz\CS_Homework\vits_with_chatgpt-gpt3\venv\lib\site-packages\transformers\generation\utils.py", line 1437, in generate
return self.sample(
File "D:\EmiyaKatuz\CS_Homework\vits_with_chatgpt-gpt3\venv\lib\site-packages\transformers\generation\utils.py", line 2440, in sample
model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)
File "C:\Users\19110/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py", line 1091, in prepare_inputs_for_generation
mask_positions = [seq.index(mask_token) for seq in seqs]
File "C:\Users\19110/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py", line 1091, in
mask_positions = [seq.index(mask_token) for seq in seqs]
ValueError: 150001 is not in list

from vits_with_chatgpt-gpt3.

直接键入网址 127.0.0.1:8080/chat?Text=测试 试一下

from vits_with_chatgpt-gpt3.

显示500 Internal Server Error，是服务端哪里没配置好么？

from vits_with_chatgpt-gpt3.

这要看服务器端的报错，光是启动成功还不够，你用chatgpt能行吗

from vits_with_chatgpt-gpt3.

我去稍微研究了一下 150001是分词规则更新造成的gmask错误 去仓库将模型、tokenizer_config.json、ice_text.model和tokenization_chatglm.py更新成最新版本 就能移除embedding中的image token以避免报错
然后，
在configuration_chatglm.py中需要将logger.warning_once修改成logger.warning就能正常运行了
不然会报AttributeError: 'Logger' object has no attribute 'warning_once'
BTW，
GLM对于关键库的版本似乎卡得很死，我这边测试下来protobuf必须为3.20.0、transformers必须为4.26.1才能正常生成回答和语音 不确定是否是个例 如果不是的话，requirements里的版本约束可能做一下修改会比较好

十分感谢您对我问题的持续解答，辛苦了

from vits_with_chatgpt-gpt3.