Pre-training
BakingBrains opened this issue · comments
Syed Abdul Gaffar Shakhadri commented
python run_pretrain.py --datadir Audio_Dir \
--labelpath Label_Path
--labeling_method hard \
--saving_path Saving_Path \
--training_step 10000 \
--save_top_k 1 \
--wav2vecpath Wav2vecCKPT \
--precision 16
Here --labelpath, should be a session label or metalabel.json?
Li-Wei Chen commented
In my experiment I only use session label since I don't want the test set to be revealed during pre-training, metalabel.json
is simply a by-product.
But if you don't care, you can feed metalabel.json
into it, it will pre-train on all of the IEMOCAP data regardless of the splits and the categories.
Syed Abdul Gaffar Shakhadri commented
@b04901014 Thank you