Closed SeanChenxy closed 2 months ago
Hey! You don't need fairseq. You could just copy the model definition from fairseq into a file so you can load the pretrained wav2vec model. Alternatively, if you want to train from scratch, you can plug in any audio encoder of your choice, e.g. a wav2vec from another codebase than fairseq that you might have access to.
Hi, thanks for sharing the excellent work. I am trying to run this repo, but
fairseq
cannot be correctly imported because of the low version ofGLIBC
. I cannot update my environment. Hene, I wonder whether there are other methods without the use offairseq
. Thanks in advance.