Download Hugging face Model failed
OSError: Can't load the model for 'facebook/wav2vec2-base-960h'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'facebook/wav2vec2-base-960h' is the correct path to a directory containing a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.\n
The above exception was the direct cause of the following exception:\n
RuntimeError: Data processing error: I/O error: Permission denied (os error 13)\n
it failed since today.
I have this setting in my docker file:
ENV TRANSFORMERS_CACHE=/tmp/hf_cache
RUN mkdir -p /tmp/hf_cache && chmod 777 /tmp/hf_cache
3 Replies
Hi, I think I get the clue of this issue, all the temp file write seems to fail.
start with /tmp.
Does /tmp identify as tempfs
yes, it was working 1 days ago, I was using it for a long time.
we have located the problem to model download, the /tmp overall seems fine.
We resolved the problem by using the pre-downloaded weights.