V4模型推理界面打不开，用v3模型进入推理界面切换v4模型还是推理不了 #2340

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Closed

xiaohuoxing opened this issue Apr 29, 2025 · 9 comments

xiaohuoxing commented Apr 29, 2025

G:\AI\GPT-SoVITS-v4-20250422fix>runtime\python.exe -I webui.py zh_CN
Running on local URL: http://0.0.0.0:9874
"G:\AI\GPT-SoVITS-v4-20250422fix\runtime\python.exe" GPT_SoVITS/inference_webui.py "zh_CN"
SoVITS_weights_v4/xinru5_e2_s298_l128.pth v2 v4 True
loading sovits_v4pretrained_G
loading sovits_v4_lora128
Traceback (most recent call last):
File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 453, in
init_hifigan()
File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 425, in init_hifigan
hifigan_model = Generator(
TypeError: init() got an unexpected keyword argument 'is_bias'
V4模型推理界面打不开

用v3模型进入推理界面切换v4模型还是推理不了
前端处理后的文本(每句): 春霄一刻值千金,花有清香月有阴.
6%|████▌ | 86/1500 [00:01<00:16, 85.45it/s]T2S Decoding EOS [108 -> 197]
6%|████▋ | 88/1500 [00:01<00:18, 78.04it/s]
Traceback (most recent call last):
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\queueing.py", line 522, in process_events
response = await route_utils.call_process_api(
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\route_utils.py", line 260, in call_process_api
output = await app.get_blocks().process_api(
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\blocks.py", line 1689, in process_api
result = await self.call_function(
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\blocks.py", line 1267, in call_function
prediction = await utils.async_iteration(iterator)
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 574, in async_iteration
return await iterator.anext()
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 567, in anext
return await anyio.to_thread.run_sync(
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio_backends_asyncio.py", line 867, in run
result = context.run(func, *args)
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 550, in run_sync_iterator_async
return next(iterator)
File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 733, in gen_wrapper
response = next(iterator)
File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 874, in get_tts_wav
init_hifigan()
File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 425, in init_hifigan
hifigan_model = Generator(
TypeError: init() got an unexpected keyword argument 'is_bias'

求大佬解惑

yangyuke001 commented Apr 29, 2025

用inference_webui.py跑v4模型跟你出现一样的问题，求支援

zazachao commented Apr 29, 2025

G:\AI\GPT-SoVITS-v4-20250422fix>runtime\python.exe -I webui.py zh_CN Running on local URL: http://0.0.0.0:9874 "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\python.exe" GPT_SoVITS/inference_webui.py "zh_CN" SoVITS_weights_v4/xinru5_e2_s298_l128.pth v2 v4 True loading sovits_v4pretrained_G loading sovits_v4_lora128 Traceback (most recent call last): File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 453, in init_hifigan() File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 425, in init_hifigan hifigan_model = Generator( TypeError: init() got an unexpected keyword argument 'is_bias' V4模型推理界面打不开

用v3模型进入推理界面切换v4模型还是推理不了前端处理后的文本(每句): 春霄一刻值千金,花有清香月有阴. 6%|████▌ | 86/1500 [00:01<00:16, 85.45it/s]T2S Decoding EOS [108 -> 197] 6%|████▋ | 88/1500 [00:01<00:18, 78.04it/s] Traceback (most recent call last): File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\queueing.py", line 522, in process_events response = await route_utils.call_process_api( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\route_utils.py", line 260, in call_process_api output = await app.get_blocks().process_api( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\blocks.py", line 1689, in process_api result = await self.call_function( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\blocks.py", line 1267, in call_function prediction = await utils.async_iteration(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 574, in async_iteration return await iterator.anext() File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 567, in anext return await anyio.to_thread.run_sync( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, *args) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 550, in run_sync_iterator_async return next(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 733, in gen_wrapper response = next(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 874, in get_tts_wav init_hifigan() File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 425, in init_hifigan hifigan_model = Generator( TypeError: init() got an unexpected keyword argument 'is_bias'

求大佬解惑

你是v3和v4版本的代码都放在一起吗，这个应该是你调用了v3的Generator。改一下路径就行，或者在推理开头设置一下就行，可以参考一下这个：
import sys
sys.path = [
'这里放你目前存放v4版本的路径（绝对路径），到GPT-SoVITS这级目录'
] + sys.path

Author

xiaohuoxing commented Apr 29, 2025

G:\AI\GPT-SoVITS-v4-20250422fix>runtime\python.exe -I webui.py zh_CN Running on local URL: http://0.0.0.0:9874 "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\python.exe" GPT_SoVITS/inference_webui.py "zh_CN" SoVITS_weights_v4/xinru5_e2_s298_l128.pth v2 v4 True loading sovits_v4pretrained_G loading sovits_v4_lora128 Traceback (most recent call last): File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 453, in init_hifigan() File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 425, in init_hifigan hifigan_model = Generator( TypeError: init() got an unexpected keyword argument 'is_bias' V4模型推理界面打不开
用v3模型进入推理界面切换v4模型还是推理不了前端处理后的文本(每句): 春霄一刻值千金,花有清香月有阴. 6%|████▌ | 86/1500 [00:01<00:16, 85.45it/s]T2S Decoding EOS [108 -> 197] 6%|████▋ | 88/1500 [00:01<00:18, 78.04it/s] Traceback (most recent call last): File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\queueing.py", line 522, in process_events response = await route_utils.call_process_api( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\route_utils.py", line 260, in call_process_api output = await app.get_blocks().process_api( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\blocks.py", line 1689, in process_api result = await self.call_function( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\blocks.py", line 1267, in call_function prediction = await utils.async_iteration(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 574, in async_iteration return await iterator.anext() File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 567, in anext return await anyio.to_thread.run_sync( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, *args) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 550, in run_sync_iterator_async return next(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 733, in gen_wrapper response = next(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 874, in get_tts_wav init_hifigan() File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 425, in init_hifigan hifigan_model = Generator( TypeError: init() got an unexpected keyword argument 'is_bias'
求大佬解惑

你是v3和v4版本的代码都放在一起吗，这个应该是你调用了v3的Generator。改一下路径就行，或者在推理开头设置一下就行，可以参考一下这个：

并没有放一起，改路径没用；
大佬这个 import sys sys.path = [ '这里放你目前存放v4版本的路径（绝对路径），到GPT-SoVITS这级目录' ] + sys.path放在哪里？我不到啊！

zazachao commented Apr 29, 2025

G:\AI\GPT-SoVITS-v4-20250422fix>runtime\python.exe -I webui.py zh_CN Running on local URL: http://0.0.0.0:9874 "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\python.exe" GPT_SoVITS/inference_webui.py "zh_CN" SoVITS_weights_v4/xinru5_e2_s298_l128.pth v2 v4 True loading sovits_v4pretrained_G loading sovits_v4_lora128 Traceback (most recent call last): File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 453, in init_hifigan() File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 425, in init_hifigan hifigan_model = Generator( TypeError: init() got an unexpected keyword argument 'is_bias' V4模型推理界面打不开
用v3模型进入推理界面切换v4模型还是推理不了前端处理后的文本(每句): 春霄一刻值千金,花有清香月有阴. 6%|████▌ | 86/1500 [00:01<00:16, 85.45it/s]T2S Decoding EOS [108 -> 197] 6%|████▋ | 88/1500 [00:01<00:18, 78.04it/s] Traceback (most recent call last): File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\queueing.py", line 522, in process_events response = await route_utils.call_process_api( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\route_utils.py", line 260, in call_process_api output = await app.get_blocks().process_api( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\blocks.py", line 1689, in process_api result = await self.call_function( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\blocks.py", line 1267, in call_function prediction = await utils.async_iteration(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 574, in async_iteration return await iterator.anext() File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 567, in anext return await anyio.to_thread.run_sync( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, *args) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 550, in run_sync_iterator_async return next(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 733, in gen_wrapper response = next(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 874, in get_tts_wav init_hifigan() File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 425, in init_hifigan hifigan_model = Generator( TypeError: init() got an unexpected keyword argument 'is_bias'
求大佬解惑

你是v3和v4版本的代码都放在一起吗，这个应该是你调用了v3的Generator。改一下路径就行，或者在推理开头设置一下就行，可以参考一下这个：

并没有放一起，改路径没用；大佬这个 import sys sys.path = [ '这里放你目前存放v4版本的路径（绝对路径），到GPT-SoVITS这级目录' ] + sys.path放在哪里？我不到啊！

放在inference_webui.py代码的开头试一下。
就比如这样：

Author

xiaohuoxing commented Apr 29, 2025

G:\AI\GPT-SoVITS-v4-20250422fix>runtime\python.exe -I webui.py zh_CN Running on local URL: http://0.0.0.0:9874 "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\python.exe" GPT_SoVITS/inference_webui.py "zh_CN" SoVITS_weights_v4/xinru5_e2_s298_l128.pth v2 v4 True loading sovits_v4pretrained_G loading sovits_v4_lora128 Traceback (most recent call last): File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 453, in init_hifigan() File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 425, in init_hifigan hifigan_model = Generator( TypeError: init() got an unexpected keyword argument 'is_bias' V4模型推理界面打不开
用v3模型进入推理界面切换v4模型还是推理不了前端处理后的文本(每句): 春霄一刻值千金,花有清香月有阴. 6%|████▌ | 86/1500 [00:01<00:16, 85.45it/s]T2S Decoding EOS [108 -> 197] 6%|████▋ | 88/1500 [00:01<00:18, 78.04it/s] Traceback (most recent call last): File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\queueing.py", line 522, in process_events response = await route_utils.call_process_api( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\route_utils.py", line 260, in call_process_api output = await app.get_blocks().process_api( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\blocks.py", line 1689, in process_api result = await self.call_function( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\blocks.py", line 1267, in call_function prediction = await utils.async_iteration(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 574, in async_iteration return await iterator.anext() File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 567, in anext return await anyio.to_thread.run_sync( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, *args) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 550, in run_sync_iterator_async return next(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\runtime\lib\site-packages\gradio\utils.py", line 733, in gen_wrapper response = next(iterator) File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 874, in get_tts_wav init_hifigan() File "G:\AI\GPT-SoVITS-v4-20250422fix\GPT_SoVITS\inference_webui.py", line 425, in init_hifigan hifigan_model = Generator( TypeError: init() got an unexpected keyword argument 'is_bias'
求大佬解惑

你是v3和v4版本的代码都放在一起吗，这个应该是你调用了v3的Generator。改一下路径就行，或者在推理开头设置一下就行，可以参考一下这个：

并没有放一起，改路径没用；大佬这个 import sys sys.path = [ '这里放你目前存放v4版本的路径（绝对路径），到GPT-SoVITS这级目录' ] + sys.path放在哪里？我不到啊！

放在inference_webui.py代码的开头试一下。就比如这样：

这样吗？还是不行。。。

xiaohuoxing closed this as completed

yangyuke001 commented May 6, 2025

@xiaohuoxing 请问你的问题解决了吗？我还有一样的问题，求指导

Author

xiaohuoxing commented May 6, 2025

没有解决😂当时没注意看把提问给关闭了，那老哥也回复不了我，我也懒得折腾了。

@xiaohuoxing 请问你的问题解决了吗？我还有一样的问题，求指导

xiaohuoxing reopened this

Author

xiaohuoxing commented May 6, 2025

@xiaohuoxing 请问你的问题解决了吗？我还有一样的问题，求指导

我发现这文件大小不一，但下载替换问题依旧。。。

xiaohuoxing closed this as completed

xiaohuoxing reopened this

xiaohuoxing closed this as completed

xiaohuoxing reopened this

Author

xiaohuoxing commented May 6, 2025

@xiaohuoxing 请问你的问题解决了吗？我还有一样的问题，求指导

我重新解压整合包可以用V4模型启动wenui了但是，我用之前训练的V4模型来推理，推理出来的文件不知道那是什么鸟语不是普通话/粤语/英文😂
现在重新训练试试看。。。

xiaohuoxing mentioned this issue

V2版整合包训练模型全部都正常，V3V4版整合包开头进度条“卡住不动” #2359

Open

xiaohuoxing closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment