[ISSUE]: Voice not converting

WrathOfMci commented 5 months ago

Voice Changer Version

MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.17b.zip

Operational System

Windows 11

GPU

NIVIDA GeForce RTX 3060

Read carefully and check the options

[X] 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

My voice won't conert to the Ai's

Application Screenshot

![Uploading image.png…]()

Logs on console

C:\Users\macke\Downloads\MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.17b\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://<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... done 200 [2024-01-15 23:30:04] connet sid : cUDX_El2wmLYEUN8AAAC [2024-01-15 23:30:04] connet sid : GkGc5OATvNgRyI-kAAAD [Voice Changer] update configuration: modelSlotIndex 1705379412000 [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'. [Voice Changer] update configuration: f0Detector crepe [Voice Changer] update configuration: silentThreshold 0.00002 [Voice Changer] update configuration: silentThreshold 0.00003 [Voice Changer] update configuration: silentThreshold 0.00007 [Voice Changer] update configuration: silentThreshold 0.00011 [Voice Changer] update configuration: silentThreshold 0.00015 [Voice Changer] update configuration: silentThreshold 0.00022 [Voice Changer] update configuration: silentThreshold 0.00031 [Voice Changer] update configuration: silentThreshold 0.00042 [Voice Changer] update configuration: silentThreshold 0.00052 [Voice Changer] update configuration: silentThreshold 0.00064 [Voice Changer] update configuration: silentThreshold 0.00075 [Voice Changer] update configuration: silentThreshold 0.00084 [Voice Changer] update configuration: silentThreshold 0.00092 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: silentThreshold 0.001 [Voice Changer] update configuration: serverReadChunkSize 384 [Voice Changer] update configuration: crossFadeEndRate 3 [Voice Changer] update configuration: crossFadeEndRate 2 [Voice Changer] update configuration: crossFadeEndRate 1 [Voice Changer] update configuration: passThrough true

lenore-puwawa commented 5 months ago

[Voice Changer] update configuration: passThrough true Please turn off the pass-through function.

WrathOfMci commented 5 months ago

[Voice Changer] update configuration: passThrough true Please turn off the pass-through function.

Yea but when I do that how would I know if it's working or not. I'm not able to hear myself. I've tried recording my voice and it wasn't converted.

lenore-puwawa commented 5 months ago

This is when the pass-through function is off.

This is when the pass-through function is on.

If you want to hear the converted audio, please set the speakers you are using as Monitor. Alternatively, change the Windows settings to listen to the virtual audio specified in Output.

WrathOfMci commented 5 months ago

This is when the pass-through function is off.

This is when the pass-through function is on.

If you want to hear the converted audio, please set the speakers you are using as Monitor. Alternatively, change the Windows settings to listen to the virtual audio specified in Output.

I disabled pass-through. I tried setting my headphones as my monitor and it didn't work. I can't hear my voice. I'm pretty sure I changed the windows setting.

C:\Users\macke\Downloads\MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.17b\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://<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 [2024-01-25 23:35:18] connet sid : BI93u_MIouDdVIr9AAAB [2024-01-25 23:35:18] connet sid : AOXo4l9Up21I1pgvAAAD [Voice Changer] update configuration: passThrough true [Voice Changer] update configuration: passThrough false [Voice Changer] update configuration: f0Detector rmvpe_onnx [Voice Changer] update configuration: f0Detector crepe [Voice Changer] update configuration: passThrough true [Voice Changer] update configuration: passThrough false [Voice Changer] update configuration: passThrough true [Voice Changer] update configuration: passThrough false [Voice Changer] update configuration: modelSlotIndex 1706244490000 [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'. [Voice Changer] update configuration: modelSlotIndex 1706244491001 [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'. [Voice Changer] update configuration: modelSlotIndex 1706244492000 [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'.

lenore-puwawa commented 5 months ago

[Voice Changer] exception! loading inferencer invalid load key, '\x08'. The sample model may be corrupted. Please check the following steps.

Does it work with other sample models (Amitaro, etc.)
If you have a suitable RVC model on hand, try it
After removing VC Client, download again & run start_http.bat（This is because a sample model is downloaded when you start it for the first time.）

For reference, the file size of the sample model (Tsukuyomi-chan) I have is 54085 KB (52.8 MB (55,382,411 byte)). It should be stored in "tsukuyomi_v2_40k_e100_simple.onnx" in "MMVCServerSIO\model_dir\0". If the file size is smaller than this, the sample model may be corrupted.

w-okada / voice-changer