Stuck on Successfully opened dynamic library cudnn64_7.dll

[jtpaquet]

I did all the installations and when I record myself and press on Synthetize only I get stuck on this line in the CLI:

2021-02-10 00:45:37.068088: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll

The GUI stop responding and it says: Loading the synthesizer synthesizer\saved models\logs-pretrained\taco_pretrained\tacotron_model.ckpt-278000

One thing I could add is that I can't load the package webrtcvad:

`E:\Other\Voices\Real-Time-Voice-Cloning-master\encoder\audio.py:13: UserWarning: Unable to import 'webrtcvad'. This package enables noise removal and is recommended. warn("Unable to import 'webrtcvad'. This package enables noise removal and is recommended.") 2021-02-10 00:43:29.707998: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll Arguments: datasets_root: None enc_models_dir: encoder\saved_models syn_models_dir: synthesizer\saved_models voc_models_dir: vocoder\saved_models low_mem: False seed: None no_mp3_support: False

Warning: you did not pass a root directory for datasets as argument. The recognized datasets are: LibriSpeech/dev-clean LibriSpeech/dev-other LibriSpeech/test-clean LibriSpeech/test-other LibriSpeech/train-clean-100 LibriSpeech/train-clean-360 LibriSpeech/train-other-500 LibriTTS/dev-clean LibriTTS/dev-other LibriTTS/test-clean LibriTTS/test-other LibriTTS/train-clean-100 LibriTTS/train-clean-360 LibriTTS/train-other-500 LJSpeech-1.1 VoxCeleb1/wav VoxCeleb1/test_wav VoxCeleb2/dev/aac VoxCeleb2/test/aac VCTK-Corpus/wav48 Feel free to add your own. You can still use the toolbox by recording samples yourself.`

The CLI since the loading checkpoint:

Loading checkpoint: synthesizer\saved_models\logs-pretrained\taco_pretrained\tacotron_model.ckpt-278000 2021-02-10 00:44:03.798882: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 2021-02-10 00:44:03.806050: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll 2021-02-10 00:44:03.831446: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce RTX 3080 major: 8 minor: 6 memoryClockRate(GHz): 1.785 pciBusID: 0000:21:00.0 2021-02-10 00:44:03.831538: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll 2021-02-10 00:44:03.835372: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll 2021-02-10 00:44:03.838306: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_100.dll 2021-02-10 00:44:03.839463: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_100.dll 2021-02-10 00:44:03.843225: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_100.dll 2021-02-10 00:44:03.845400: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_100.dll 2021-02-10 00:44:03.852431: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll 2021-02-10 00:44:03.852557: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2021-02-10 00:44:58.939104: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2021-02-10 00:44:58.939228: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2021-02-10 00:44:58.941133: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2021-02-10 00:44:58.941796: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 8551 MB memory) -> physical GPU (device: 0, name: GeForce RTX 3080, pci bus id: 0000:21:00.0, compute capability: 8.6) 2021-02-10 00:44:59.515354: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll 2021-02-10 00:45:37.068088: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll

Am I missing something?

thx

[ghost]

Tensorflow 1.x is not compatible with NVIDIA 30xx GPUs. I have a pull request to remove this dependency, it is in the final stages of review. It's already released in my fork if you don't want to wait. https://github.com/blue-fish/Real-Time-Voice-Cloning

[jtpaquet]

That was it, I tried on my roommate's pc with a GTX 1060 and it worked with no problems, thanks

[ghost]

Closing this issue, #472 is merged and removes the dependency on tensorflow.