Open ZHTushar23 opened 1 year ago
I don't observe the same error with that command. Could you share the details of your environment and libraries?
I am using an anaconda3 environment. Here is the list of packages that are installed in this environment.
_libgcc_mutex 0.1 main
_openmp_mutex 5.1 1_gnu
audlib 0.0.3.3 pypi_0 pypi
ca-certificates 2023.01.10 h06a4308_0
certifi 2022.12.7 py39h06a4308_0
cffi 1.15.1 pypi_0 pypi
charset-normalizer 3.1.0 pypi_0 pypi
click 8.1.3 pypi_0 pypi
filelock 3.10.7 pypi_0 pypi
huggingface-hub 0.13.3 pypi_0 pypi
hyperpyyaml 1.1.0 pypi_0 pypi
idna 3.4 pypi_0 pypi
joblib 1.2.0 pypi_0 pypi
ld_impl_linux-64 2.38 h1181459_1
libffi 3.4.2 h6a678d5_6
libgcc-ng 11.2.0 h1234567_1
libgomp 11.2.0 h1234567_1
libstdcxx-ng 11.2.0 h1234567_1
llvmlite 0.39.1 pypi_0 pypi
ncurses 6.4 h6a678d5_0
numba 0.56.4 pypi_0 pypi
numpy 1.23.5 pypi_0 pypi
openssl 1.1.1t h7f8727e_0
packaging 23.0 pypi_0 pypi
pillow 9.4.0 pypi_0 pypi
pip 23.0.1 py39h06a4308_0
pycparser 2.21 pypi_0 pypi
python 3.9.16 h7a1cb2a_2
pyyaml 6.0 pypi_0 pypi
readline 8.2 h5eee18b_0
requests 2.28.2 pypi_0 pypi
resampy 0.4.2 pypi_0 pypi
robust-speech 0.3.1 pypi_0 pypi
ruamel-yaml 0.17.21 pypi_0 pypi
ruamel-yaml-clib 0.2.7 pypi_0 pypi
scipy 1.10.1 pypi_0 pypi
sentencepiece 0.1.97 pypi_0 pypi
setuptools 65.6.3 py39h06a4308_0
soundfile 0.12.1 pypi_0 pypi
speechbrain 0.5.13 pypi_0 pypi
sqlite 3.41.1 h5eee18b_0
tk 8.6.12 h1ccaba5_0
tokenizers 0.13.2 pypi_0 pypi
torch 1.11.0 pypi_0 pypi
torchaudio 0.11.0 pypi_0 pypi
torchvision 0.13.1+cu113 pypi_0 pypi
tqdm 4.65.0 pypi_0 pypi
transformers 4.27.3 pypi_0 pypi
typing-extensions 4.5.0 pypi_0 pypi
tzdata 2022g h04d1e81_0
urllib3 1.26.15 pypi_0 pypi
wheel 0.38.4 py39h06a4308_0
xz 5.2.10 h5eee18b_1
zlib 1.2.13 h5eee18b_0
I am using CPU to run the test.
When running the first usage example, I am facing the following RuntimeError.
RuntimeError: The size of tensor a (2) must match the size of tensor b (40) at non-singleton dimension 3.
example used: in ./recipes/
This will download the speechbrain/asr-crdnn-rnnlm-librispeech model from huggingface python evaluate.py attack_configs/LibriSpeech/pgd/s2s_1000bpe.yaml --root=/path/to/results/folder