I got W-Okada directml-cuda latest version on my 7600x-6900xt system but no sound is coming out. I've made sure to select the corresponding gpu number. Passthrough does work and returns my voice unchanged, but monitor doesn't return anything. When I hit record it'll return an empty file and for IO Analyzer, neither the in or out get recorded to.
#No conversion happening.
sharp rivet
tender tiger
I got W-Okada directml-cuda latest version on my 7600x-6900xt system but no soun...
Did you select your input and output
sharp rivet
Did you select your input and output
Yes, my input is my 3.5 mic and output is the default out which is tv speaker over hdmi.
exotic creekBOT
Ayo? @sharp rivet level 1 !!! 
tender tiger
Yes, my input is my 3.5 mic and output is the default out which is tv speaker ov...
Did you click the green start button
sharp rivet
Did you click the green start button
Yes, no sound coming out.
sharp rivet
Did you click the green start button
gloomy garden
Any CMD logs?
sharp rivet
Any CMD logs?
--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://<IP>:<PORT>/
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/
[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 25, in getInferencer
File "voice_changer\RVC\inferencer\InferencerManager.py", line 37, 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'.
[VCClient] wait web server... done 200
[2024-01-20 23:49:14] connet sid : kStQEsAhH4DQRWKrAAAB
[2024-01-20 23:49:14] connet sid : n7KkHFzbise0ZsGRAAADi
Sorry I don't have nitro I can't send it all, this is the last lines
gloomy garden
--hubert_soft pretrain/hubert/hubert-soft-0d54a1f4.pt --nsf_hifigan pretrain...
Might be an issue with the model_dir folder, try deleting and restarting W-Okada
sharp rivet
Might be an issue with the model_dir folder, try deleting and restarting W-Okada
Like delete the folder and then re extract?
gloomy garden
Like delete the folder and then re extract?
Nah just restart W-Okada
it should reinstall the files it needs
sharp rivet
it should reinstall the files it needs
I've done that multiple times now. Closed and reopened
gloomy garden
Delete the files and restart it
sharp rivet
Oh ok
sharp rivet
Delete the files *and* restart it
Yep that was it. Working flawlessly now, thanks!
gloomy garden
Yep that was it. Working flawlessly now, thanks!
Yay! Glad I could help. I'll mark this as solved.