markhershey / audiodeepfakedetection Goto Github PK

audioread==3.0.1
certifi==2023.11.17
cffi==1.16.0
charset-normalizer==3.3.2
cmake==3.27.7
colorlog==6.7.0
contourpy==1.2.0
cycler==0.12.1
decorator==5.1.1
filelock==3.13.1
fonttools==4.45.0
fsspec==2023.10.0
idna==3.4
Jinja2==3.1.2
joblib==1.3.2
kiwisolver==1.4.5
lazy_loader==0.3
librosa==0.10.1
lit==17.0.5
llvmlite==0.41.1
MarkupSafe==2.1.3
matplotlib==3.8.2
mpmath==1.3.0
msgpack==1.0.7
networkx==3.2.1
numba==0.58.1
numpy==1.26.2
nvidia-cublas-cu11==11.10.3.66
nvidia-cublas-cu12==12.1.3.1
nvidia-cuda-cupti-cu11==11.7.101
nvidia-cuda-cupti-cu12==12.1.105
nvidia-cuda-nvrtc-cu11==11.7.99
nvidia-cuda-nvrtc-cu12==12.1.105
nvidia-cuda-runtime-cu11==11.7.99
nvidia-cuda-runtime-cu12==12.1.105
nvidia-cudnn-cu11==8.5.0.96
nvidia-cudnn-cu12==8.9.2.26
nvidia-cufft-cu11==10.9.0.58
nvidia-cufft-cu12==11.0.2.54
nvidia-curand-cu11==10.2.10.91
nvidia-curand-cu12==10.3.2.106
nvidia-cusolver-cu11==11.4.0.1
nvidia-cusolver-cu12==11.4.5.107
nvidia-cusparse-cu11==11.7.4.91
nvidia-cusparse-cu12==12.1.0.106
nvidia-nccl-cu11==2.14.3
nvidia-nccl-cu12==2.18.1
nvidia-nvjitlink-cu12==12.3.101
nvidia-nvtx-cu11==11.7.91
nvidia-nvtx-cu12==12.1.105
packaging==23.2
Pillow==10.1.0
platformdirs==4.0.0
pooch==1.8.0
puts==0.0.8
pycparser==2.21
pyparsing==3.1.1
python-dateutil==2.8.2
requests==2.31.0
scikit-learn==1.3.2
scipy==1.11.4
six==1.16.0
soundfile==0.12.1
soxr==0.3.7
sympy==1.12
threadpoolctl==3.2.0
torch==2.0.1
torchaudio==2.0.2
torchinfo==1.8.0
triton==2.0.0
typing_extensions==4.8.0
urllib3==2.1.0

This is the modules installed and
i am getting this error
Could not load library libcudnn_cnn_infer.so.8. Error: libcuda.so: cannot open shared object file: No such file or directory
this error coming after downgraded the torchaudio to 2.0.2

i had the a different error while training with torchaudio 2.1.1 the error was raise RuntimeError(
RuntimeError: apply_effects_file requires sox extension which is not available. Please refer to the stacktrace above for how to resolve this. how to resolve these two errors

I was wondering if after I trained my data, is it possible to use my own voice clip to detect if it is fake or not?

Hi,

I've made some modifications to the code to ensure compatibility with Windows, specifically addressing the Sox dependency with torchaudio by using Sox independently. Other than that, I've kept the original setup intact.

However, I've encountered an issue when using the eval_one function. Every audio input, whether genuine or fake, is consistently classified as fake (output always equals 1). This behavior is observed even when testing on authentic audio files.

I'd like to understand the correct procedure to utilize the lfcc ShallowCNN model that you've provided for evaluating audio files. Since I don't have an NVIDIA GPU, training is quite time-intensive for me, and I'm keen on testing the pre-trained model you've developed on new RVC voice-generated samples and others.

Any guidance on how to successfully test the model would be greatly appreciated. Thank you!

when i run the evaluation code it is showing this error

2023-11-23 12:08:00,216 - ERROR - 'bool' object is not callable
Traceback (most recent call last):
File "/home/pradeep/AudioDeepFakeDetection/train.py", line 593, in main
experiment(
File "/home/pradeep/AudioDeepFakeDetection/train.py", line 430, in experiment
eval_only(
TypeError: 'bool' object is not callable

Inference a single audio file using the PyTorch model and add into the GUI

I have been trying to use your model in the google drive (best.pt) model and tried to preprocess it however I keep getting different types of errors whenever I try changing something. Such as:

RuntimeError: mat1 and mat2 shapes cannot be multiplied (1x241152 and 15104x128)
RuntimeError: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [1, 1, 1, 40, 64600]

I am trying to do something just like your website where given the audio it displays real or fake. Is there any code or reference?