Skip to content
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

[ISSUE]: Voice changer not making sound #1386

Open
4 of 6 tasks
ch382 opened this issue Oct 20, 2024 · 5 comments
Open
4 of 6 tasks

[ISSUE]: Voice changer not making sound #1386

ch382 opened this issue Oct 20, 2024 · 5 comments

Comments

@ch382
Copy link

ch382 commented Oct 20, 2024

Voice Changer Version

MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.18a

Operational System

Windows 10

GPU

intel UHD graphics 620

Read carefully and check the options

  • I've tried to Clear Settings
  • Sample/Default Models are working
  • I've tried to change the Chunk Size
  • GUI was successfully launched
  • I've read the tutorial
  • I've tried to extract to another folder (or re-extract) the .zip file

Model Type

RVC

Issue Description

I made sure the input and output devices are correct, I tried recording my voice and it doesn't play anything. I have it set to CPU but the CPU isn't being used at all, neither the GPU.

Application Screenshot

image_2024-10-19_203512027

Logs on console

C:\Users\miranda\Downloads\MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.18a\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
Booting PHASE :main
PYTHON:3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]
Activating the Voice Changer.
[Voice Changer] download sample catalog. samples_0004_t.json
[Voice Changer] download sample catalog. samples_0004_o.json
[Voice Changer] download sample catalog. samples_0004_d.json
[Voice Changer] model_dir is already exists. skip download samples.
Internal_Port:18888
protocol: HTTP
-- ---- --
Please open the following URL in your browser.
http://:/
In many cases, it will launch when you access any of the following URLs.
http://127.0.0.1:18888/

[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:CPU-DML)
[Voice Changer][RVC]: update_settings gpu:-1
[Voice Changer][RVCr2] Initializing...
[VCClient] wait web server...10 http://127.0.0.1:18888/
[Voice Changer] generate new embedder. (no embedder)
[Voice Changer] Loading index...
[Voice Changer] Index file is not found
GENERATE INFERENCER<voice_changer.RVC.inferencer.OnnxRVCInferencer.OnnxRVCInferencer object at 0x00000241EDE73C70>
GENERATE EMBEDDER<voice_changer.RVC.embedder.OnnxContentvec.OnnxContentvec object at 0x00000241EDEFC850>
GENERATE PITCH EXTRACTOR<voice_changer.RVC.pitchExtractor.RMVPEOnnxPitchExtractor.RMVPEOnnxPitchExtractor object at 0x00000241EDEFC8B0>
[Voice Changer] [RVC] Initializing... done
[Voice Changer][RVC]: update_settings serverReadChunkSize:192
[Voice Changer][RVC]: update_settings f0Detector:rmvpe_onnx
[Voice Changer][RVC]: update_settings modelSlotIndex:1729390653000
[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
[2024-10-19 20:33:17] connet sid : ftz_0CNhdl6nMymrAAAC
[2024-10-19 20:33:17] connet sid : QrOuIaUy4SiiTPzDAAAD
Generated Strengths: for prev:(4096,), for cur:(4096,)
[Voice Changer] warming up... generating sola buffer.
[Voice Changer] update configuration: tran 8
[Voice Changer][RVC]: update_settings tran:8
[Voice Changer] update configuration: tran 11
[Voice Changer][RVC]: update_settings tran:11
[Voice Changer] update configuration: tran 14
[Voice Changer][RVC]: update_settings tran:14
[Voice Changer] update configuration: tran 17
[Voice Changer][RVC]: update_settings tran:17
[Voice Changer] update configuration: tran 20
[Voice Changer][RVC]: update_settings tran:20
[Voice Changer] update configuration: tran 23
[Voice Changer][RVC]: update_settings tran:23
[Voice Changer] update configuration: tran 31
[Voice Changer] update configuration: tran 33
[Voice Changer][RVC]: update_settings tran:31
[Voice Changer] update configuration: tran 26
[Voice Changer][RVC]: update_settings tran:33
[Voice Changer] update configuration: tran 36
[Voice Changer] update configuration: tran 28
[Voice Changer] update configuration: tran 39
[Voice Changer][RVC]: update_settings tran:28
[Voice Changer][RVC]: update_settings tran:36
[Voice Changer][RVC]: update_settings tran:39
[Voice Changer][RVC]: update_settings tran:26
[Voice Changer] update configuration: tran 42
[Voice Changer][RVC]: update_settings tran:42
[Voice Changer] update configuration: tran 45
[Voice Changer] update configuration: tran 47
[Voice Changer] update configuration: tran 47
[Voice Changer] update configuration: tran 48
[Voice Changer] update configuration: tran 47
[Voice Changer][RVC]: update_settings tran:45
[Voice Changer][RVC]: update_settings tran:47
[Voice Changer][RVC]: update_settings tran:48
[Voice Changer][RVC]: update_settings tran:47
[Voice Changer][RVC]: update_settings tran:47
[Voice Changer] update configuration: tran 46
[Voice Changer][RVC]: update_settings tran:46
[Voice Changer] update configuration: tran 44
[Voice Changer] update configuration: tran -21
[Voice Changer] update configuration: tran -21
[Voice Changer] update configuration: tran -19
[Voice Changer] update configuration: tran -19
[Voice Changer][RVC]: update_settings tran:44
[Voice Changer][RVC]: update_settings tran:-21
[Voice Changer][RVC]: update_settings tran:-21
[Voice Changer][RVC]: update_settings tran:-19
[Voice Changer][RVC]: update_settings tran:-19
[Voice Changer] update configuration: tran -9
[Voice Changer][RVC]: update_settings tran:-9
[Voice Changer] update configuration: tran -8
[Voice Changer][RVC]: update_settings tran:-8
[Voice Changer] update configuration: tran -8
[Voice Changer][RVC]: update_settings tran:-8
[Voice Changer] update configuration: tran -6
[Voice Changer] update configuration: tran 3
[Voice Changer] update configuration: tran 4
[Voice Changer][RVC]: update_settings tran:-6
[Voice Changer][RVC]: update_settings tran:3
[Voice Changer][RVC]: update_settings tran:4
[Voice Changer] update configuration: tran 7
[Voice Changer][RVC]: update_settings tran:7
[Voice Changer] update configuration: tran 17
[Voice Changer][RVC]: update_settings tran:17
[Voice Changer] update configuration: tran 43
[Voice Changer][RVC]: update_settings tran:43
[Voice Changer] update configuration: tran 50
[Voice Changer][RVC]: update_settings tran:50
[2024-10-19 20:34:45] connet sid : Hz4PmdDLzJeoNbZcAAAF
@Kuuko-fokkusugaru
Copy link

Try lowering the chunk to 96. You are getting a huge delay, I think the CPU may not be capable of converting properly due lack of performance. You can try a different F0 detection like "dio", which is meant to use the CPU and is the lightweight one. You also have "harvest" which is the high-precision one (may be slower).
Also, I recommend to not set TUNE to 50 because that's the pitch. For male to female conversion, use around 12 depending on how deep your voice is. For female to male, use -12. For male to male or female to female, you may need to use numbers between -4 and 4.

@ch382
Copy link
Author

ch382 commented Oct 20, 2024

I was changing the tune because before I couldn't change it, and also how do you get the "dio" F0 detection? For me I only have the crepe_tiny and the rmvpe_onnx ones. Also what is "harvest"? Thanks

@Kuuko-fokkusugaru
Copy link

I guess the ml version haven't those F0 detection methods. Different methods requires more or less cpu or gpu but in your case you may be restricted to only those two. It may be the case that your cpu may not be strong enough for RVC. A high end gpu is highly recommend for a good performance.

But before giving up, try to use the newer version 2 of the software. In your case you may look for the standard version, not the CUDA one. You can find the latest v1 and v2 here:

https://huggingface.co/wok000/vcclient000/tree/main

Let's see if v2 gives you better results. Try first with the default settings. I'd also recommend to try with a pth model instead of onnx (you can download the default ones in pth format from the software itself when you click on edit to add new voices or just download a free random one to test). Onnx models, as far I know, may benefit more from the GPU which isn't your case. It's not like they can't work with cpu but maybe for your cpu may not be the most optimal scenario. Just try and good luck!

@ch382
Copy link
Author

ch382 commented Oct 20, 2024

It's making sound but its delayed and speaking gibberish, the delay is a lot more than it says on the "convert" sign, I also can't change any settings for s
image_2024-10-20_144915001
ome reason

@Kuuko-fokkusugaru
Copy link

Try different F0 detection methods to see if any gives better results but, like I mentioned, RVC needs a very strong GPU to work better.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@Kuuko-fokkusugaru @ch382