-
Notifications
You must be signed in to change notification settings - Fork 1.9k
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.
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
[ISSUE]:Voice Changer] Pipeline is not initialized. [Voice Changer] Waiting generate pipeline... #1443
Comments
I'm fairly new to github, so forgive me if I input some of the format wrong |
Since you're not using a GPU, you should download the direct ml version instead of the CUDA one. Give it a try. And if doesn't work, try the v2 too. In the case of v2, it's marked as standard (std). |
Good, but how do I Uninstall this one first? (Mb, I'm kinda slow and need detailed instructions to get things working) (I'm saying this because the installation process downloaded some other stuff onto my pc, forgive me if I'm not specific enough) |
I had also come to a stuck in installing the correct one, may you please specify which one is the ML one? (The one with ML also says Cuda so I'm not sure) |
The software doesn't installs, it just decompress so all you have to do is delete the folder where you decompressed it. For v2: https://huggingface.co/wok000/vcclient000/blob/main/vcclient_win_std_2.0.73-beta.zip |
I'll try it, and see if it works. I'll update the situation in abit |
Bad news I got the same problem but with different Errors C:\Users\DELL\Downloads\MMVCServerSIO>MMVCServerSIO.exe -p 18888 --https false --content_vec_500 pretrain/checkpoint_best_legacy_500.pt --content_vec_500_onnx pretrain/content_vec_500.onnx --content_vec_500_onnx_on true --hubert_base pretrain/hubert_base.pt --hubert_base_jp pretrain/rinna_hubert_base_jp.pt --hubert_soft pretrain/hubert/hubert-soft-0d54a1f4.pt --nsf_hifigan pretrain/nsf_hifigan/model --crepe_onnx_full pretrain/crepe_onnx_full.onnx --crepe_onnx_tiny pretrain/crepe_onnx_tiny.onnx --rmvpe pretrain/rmvpe.pt --model_dir model_dir --samples samples.json [VCClient] Access http://127.0.0.1:18888/ |
And for the V2 it doesn't even launch |
[Voice Changer] model slot is changed 0 -> 1 |
I tried using Passthru on V1, it worked but my voice wasn't altered in any way, and it only worked once before muting once more and I couldn't select any other model |
Pass-through is indeed made so you can hear your voice instead of the converted one. Do you launch the software using start_http.bat? Try decompressing the software in a folder inside of the root of a different drive other than C. If you haven't extra drives then do it inside of a folder in C, don't do it in the downloads folder or desktop. Try using the default settings other than changing the input and output devices so you can use your mic and listen. Let's see if it works not changing anything else. Also, which cpu model do you have? |
I do already have it on a folder on C, I can move it to another driver if You want me to, I'll test that thing out and use the default settings, I'll update to You in a few minutes |
Intel(R) Core(TM) i5-3570 CPU @ 3.40GHz 3.40 GHz |
I do launch it using start |
Bad news, I can't even select the models for it to work now, and the errors are the exact same [Voice Changer] update configuration: modelSlotIndex 1738422376000 [Voice Changer] update configuration: modelSlotIndex 1738422378000 Full code here | H:\MMVCServerSIO>MMVCServerSIO.exe -p 18888 --https false --content_vec_500 pretrain/checkpoint_best_legacy_500.pt --content_vec_500_onnx pretrain/content_vec_500.onnx --content_vec_500_onnx_on true --hubert_base pretrain/hubert_base.pt --hubert_base_jp pretrain/rinna_hubert_base_jp.pt --hubert_soft pretrain/hubert/hubert-soft-0d54a1f4.pt --nsf_hifigan pretrain/nsf_hifigan/model --crepe_onnx_full pretrain/crepe_onnx_full.onnx --crepe_onnx_tiny pretrain/crepe_onnx_tiny.onnx --rmvpe pretrain/rmvpe.pt --model_dir model_dir --samples samples.json [VCClient] Access http://127.0.0.1:18888/ [Voice Changer] update configuration: modelSlotIndex 1738422378000 Falling back to ['CPUExecutionProvider'] and retrying. [Voice Changer] [RVCr2] Creating instance |
I didn't ask to move the folder, I mentioned to decompress into a new folder inside of the root of your drive. Moving the folder may break it as the downloaded files by RVC may point to wrong locations. That said, I feel like trying to run the software in a such low end computer may never work. RVC works better with a high end GPU, your computer doesn't even have a dedicated GPU a d the CPU is an old low end model, sorry. Even running it on high end CPUs is a bit tricky sometimes. I recommend a computer with at least a nvidia 3060 or 4060 minimum. And if you want to be able to use RVC while gaming, you need at least a nvidia 3080, 3080Ti, 4080, 4080 super, or superior. |
Some forks of the project are meant to run in lower end computers so you could try that. But I haven't tested any so I am not in position to recommend one. Good luck though! |
You can try this one but I haven't tried yet myself so attempt at your own risk. Let me know if this one works for you. https://github.com/deiteris/voice-changer?tab=readme-ov-file#overview |
Oh Okay, thanks.. (Sir or ma'am) for your time, I will take your words into consideration and will Update the situation to you in abit |
Uhm, how do I move the folder exactly? Maybe detailed instructions? |
Tell me how do I install it with instructions please |
Create a new folder inside of the C drive and name it whatever, like RVC for example. Open the file that you downloaded and click on extract. Once prompted where to extract the file, point to the empty folder that you just created named RVC and click proceed. That should give you a clean new installation. |
How do I use this one? I installed it but the Exe got an error and created a temp file when I tried opening it |
That is what I have been doing the entire time |
Turned out to be a virus..? |
Like I said, I didn't use or test any other one than this main release so I can't help with other forks. |
Oh.. Even then, are there good alternatives to this? Because I do have the money to get a better computer, It's that I feel like it's finanically unresponsible to spend so much to only be able to use a voice changer, if there are no alternatives, it's fine |
I'm also confused on how my device is affecting the Voice Changer's performance or affecting how it works, since it only took like 5% of my CPU, You the professional and all, but I need convincing that's all, cuz maybe it's something else I don't know about yet? |
It's not using much CPU because isn't working. I can use the CPU mode but isn't optimal and I have an i7 13700K which I just got the past year. It can stutter or have a big delay plus the CPU modes haven't the same good quality than using a GPU. For GPU I have an nvidia 3080Ti, but you don't need so much only to run RVC. You just have to understand that AI based applications are very heavy and the nvidia RTX GPUs comes ready precisely for AI tasks among gaming. Your Intel i5 3000 it's like 13 years old so it will lack in any modern task, specially AI. Alternatively you can use the Google collab version of the software. Basically it means that you will run RVC off from a Google server and you access to the software through a regular browser. The instructions are on the collab link itself and are easy to follow. But, as far I know, it will only let you use the software for like 5 minutes before it stops working because Google won't allow this type of heavy tasks for free. You can pay a subscription for some resources but I have never done it. I don't know how much time is each tier of subscription available so I can't help much on that. That said, I don't know how much do you use your computer or how important it may or not be. But, considering how old your computer is already, updating to a new one, I'd you make daily use of it, shouldn't be a bad idea. You don't need to go crazy with it if you don't game. One of the latest mid range AMD Ryzen with 32GB of RAM and an nvidia 3060/4060 should be enough for daily tasks, gaming at very decent quality and smoothness, and RVC. But that depends on each people's needs. Obviously, to get a computer solely for RVC may not be the best of the ideas unless it's really important for you. |
Hmm, alright, I get it. I know it's not a good idea to get an Entire computer for it, that'll be too costly. though I am interested in what Processors you may recommend for this sort of stuff however, incase I change my mind on the matter. You had said a AMD Ryzen with 32GB of RAM and an nvidia 3060/4060, but for me that's sort of vague, no Monitor specific's no particular Computer Case, nor there of. |
Because the monitor or computer case won't make any difference in how the whole computer may perform. I recommended an AMD Ryzen because there are cheaper mid-range models so you can use the Nvidia 3060 GPU instead of the CPU. Suppose you want to use the CPU only, which I do not recommend because you will never get any closer to the performance of using a GPU instead. In that case, you should aim for one of the highest available because the software truly needs a lot of processing power like an i9 14 or one of the latest highest-end Ryzen ones. So that's it, I only mentioned the components that can be relevant for a computer to work properly in different environments, including RVC without using heavy games simultaneously. If you want to use RVC while in Discord and playing some games then you need something way stronger that can hold games and RVC. The monitor or case that's up to your taste. Some people like it big like 32-34 inches, and some people prefer smaller like 24 inches. Same for the case... some people prefer a full tower, and some prefer a mid-tower. Some may want it with space for a lot of fans, some just want the bare minimum. |
|
|
I am just a regular user, 3D artist, nothing more lol. So if you want more specifics components, what's your aim for the computer besides RVC? Which other tasks do you want to do with it? And what's your budget? Since there are too many components, depending on what you expect from the computer I can recommend different components that adjust to your budget. |
Oh lol, I thought you were some specialist in this stuff, like a contributer to RVC or something, even then Thanks for helping me and everyone else on the platform I am not sure, I would say like a good middle point, I have a 30K EGP budget which I do not know how much that translates into USD or EURO since, I'm not a westerner nor am I from a rich continent such as Europe |
Voice Changer Version
MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.18a.zip
Operational System
Windows 10
GPU
none
Read carefully and check the options
Model Type
MMVC
Issue Description
I dunno what to add, but I'll try to fill this field the best I can:
Application Screenshot
Logs on console
[VCClient] Access http://127.0.0.1:18888/
[VCClient] wait web server...0 http://127.0.0.1:18888/
Booting PHASE :main
Booting PHASE :MMVCServerSIO
[Voice Changer] VoiceChangerManager initializing...
[Voice Changer] model slot is changed -1 -> 0
................RVC
[Voice Changer] [RVCr2] Creating instance
VoiceChangerV2 Initialized (GPU_NUM(cuda):0, mps_enabled:False, onnx_device:GPU)
[Voice Changer][RVC]: update_settings gpu:0
[Voice Changer][RVCr2] Initializing...
[Voice Changer] exception! loading inferencer invalid load key, '\x08'.
Traceback (most recent call last):
File "voice_changer\RVC\pipeline\PipelineGenerator.py", line 22, in createPipeline
File "voice_changer\RVC\inferencer\InferencerManager.py", line 26, in getInferencer
File "voice_changer\RVC\inferencer\InferencerManager.py", line 38, in loadInferencer
File "voice_changer\RVC\inferencer\RVCInferencer.py", line 16, in loadModel
File "torch\serialization.py", line 815, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "torch\serialization.py", line 1033, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, '\x08'.
[Voice Changer] pipeline create failed. check your model is valid.
[Voice Changer][RVC]: update_settings enableServerAudio:0
[Voice Changer][RVC]: update_settings serverReadChunkSize:2
[Voice Changer][RVC]: update_settings f0Detector:dio
[Voice Changer][RVC]: update_settings silentThreshold:0.00006
[Voice Changer][RVC]: update_settings modelSlotIndex:1738331198000
[Voice Changer] VoiceChangerManager initializing... done.
[Voice Changer] MMVC_Rest initializing...
[Voice Changer] MMVC_Rest initializing... done.
[Voice Changer] MMVC_SocketIOApp initializing...
[Voice Changer] MMVC_SocketIOApp initializing... done.
[VCClient] wait web server... done 200
[2025-01-31 16:17:51] connet sid : jUG4Vz66iIsQxfJgAAAC
[2025-01-31 16:17:51] connet sid : enwVAPKLIIJ7VLUCAAAD
Generated Strengths: for prev:(256,), for cur:(256,)
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
The text was updated successfully, but these errors were encountered: