I know this seems similar to other threads but in most of those threads people were using an old GPU driver wheras I have an up to date driver.
I’m trying to use this piece of software on Github:
https://github.com/CorentinJ/Real-Time-Voice-Cloning
Here is the error output:
Traceback (most recent call last):
File “demo_cli.py”, line 91, in
mels = synthesizer.synthesize_spectrograms(texts, embeds)
File “C:\Users\User\Desktop\Real-Time-Voice-Cloning\synthesizer\inference.py”, line 77, in synthesize_spectrograms
self.load()
File “C:\Users\User\Desktop\Real-Time-Voice-Cloning\synthesizer\inference.py”, line 58, in load
self._model = Tacotron2(self.checkpoint_fpath, hparams)
File “C:\Users\User\Desktop\Real-Time-Voice-Cloning\synthesizer\tacotron2.py”, line 59, in init
self.session = tf.Session(config=config)
File “C:\Program Files\Python37\lib\site-packages\tensorflow\python\client\session.py”, line 1570, in init
super(Session, self).init(target, graph, config=config)
File “C:\Program Files\Python37\lib\site-packages\tensorflow\python\client\session.py”, line 693, in init
self._session = tf_session.TF_NewSessionRef(self._graph._c_graph, opts)
tensorflow.python.framework.errors_impl.InternalError: cudaGetDevice() failed. Status: CUDA driver version is insufficient for CUDA runtime version
Versions of stuff I’m using:
Windows 10
CUDA Version ( 10.0 )
CudNN Version ( 7.6.5 )
Torch version ( 1.2.0 )
torchvision ( 0.4.1 )
Tensorflow Version ( 1.14.0 ) - also tried 1.13.1, 1.13.2
GPU Driver Version - GeForce Game Ready Driver 445.75
Output of commands people usually ask for:
$ nvcc.exe --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sat_Aug_25_21:08:04_Central_Daylight_Time_2018
Cuda compilation tools, release 10.0, V10.0.130
C:\Program Files\NVIDIA Corporation\NVSMI>nvidia-smi.exe
Mon Apr 13 21:00:16 2020
±----------------------------------------------------------------------------+
| NVIDIA-SMI 445.75 Driver Version: 445.75 CUDA Version: 11.0 |
|-------------------------------±---------------------±---------------------+
| GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 1080 WDDM | 00000000:01:00.0 On | N/A |
| N/A 38C P8 6W / N/A | 1246MiB / 8192MiB | 3% Default |
±------------------------------±---------------------±---------------------+
Here is an issue I put on github with the same information: https://github.com/CorentinJ/Real-Time-Voice-Cloning/issues/321