search

facebookresearch / audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
MIT License
20.92k stars 2.14k forks source link

I don't know what error this is? #350

Open lexuwaifu opened 11 months ago

lexuwaifu commented 11 months ago

WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for: PyTorch 2.0.1+cu118 with CUDA 1108 (you have 2.0.1+cpu) Python 3.10.11 (you have 3.10.6) Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers) Memory-efficient attention, SwiGLU, sparse and more won't be available. Set XFORMERS_MORE_DETAILS=1 for more details Traceback (most recent call last): File "D:\Python\lib\runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "D:\Python\lib\runpy.py", line 86, in _run_code exec(code, run_globals) File "D:\AI\Music AI\audiocraft\demos\musicgen_app.py", line 26, in from audiocraft.data.audio_utils import convert_audio File "D:\AI\Music AI\audiocraft\audiocraft__init.py", line 24, in from . import data, modules, models File "D:\AI\Music AI\audiocraft\audiocraft\data__init__.py", line 10, in from . import audio, audio_dataset, info_audio_dataset, music_dataset, sound_dataset File "D:\AI\Music AI\audiocraft\audiocraft\data\info_audio_dataset.py", line 19, in from ..modules.conditioners import SegmentWithAttributes, ConditioningAttributes File "D:\AI\Music AI\audiocraft\audiocraft\modules\conditioners.py", line 22, in from transformers import RobertaTokenizer, T5EncoderModel, T5Tokenizer # type: ignore File "D:\Python\lib\site-packages\transformers\init__.py", line 26, in from . import dependency_versions_check File "D:\Python\lib\site-packages\transformers\dependency_versions_check.py", line 57, in require_version_core(deps[pkg]) File "D:\Python\lib\site-packages\transformers\utils\versions.py", line 117, in require_version_core return require_version(requirement, hint) File "D:\Python\lib\site-packages\transformers\utils\versions.py", line 111, in require_version _compare_versions(op, got_ver, want_ver, requirement, pkg, hint) File "D:\Python\lib\site-packages\transformers\utils\versions.py", line 44, in _compare_versions raise ImportError( ImportError: accelerate>=0.20.3 is required for a normal functioning of this module, but found accelerate==0.18.0. Try: pip install transformers -U or pip install -e '.[dev]' if you're working with git main

lamHoussam commented 11 months ago

Try creating a python virtual environment in your directory :

python -m venv env

And then activate your environment 

.\env\Scripts\activate

after that try downloading torch this way:

.\env\scripts\pip install torch==2.0.1+cu118 torchvision torchaudio

You can then install audiocraft. Here is the documentatio non virtual environments: https://docs.python.org/3/library/venv.html