vall-e
vall-e copied to clipboard
Could you please provide me with the specific parameter configurations in the command for training the LJSpeech dataset?
Could you please provide me with the specific parameter configurations in the command for training the LJSpeech dataset? Like this:
python3 bin/trainer.py --max-duration 80 --filter-min-duration 0.5 --filter-max-duration 14 --train-stage 1
--num-buckets 6 --dtype "bfloat16" --save-every-n 10000 --valid-interval 20000
--model-name valle --share-embedding true --norm-first true --add-prenet false
--decoder-dim 256 --nhead 8 --num-decoder-layers 6 --prefix-mode 1
--base-lr 0.05 --warmup-steps 200 --average-period 0
--num-epochs 20 --start-epoch 1 --start-batch 0 --accumulate-grad-steps 4
--exp-dir exp/valle
and
python3 bin/trainer.py --max-duration 40 --filter-min-duration 0.5 --filter-max-duration 14 --train-stage 2
--num-buckets 6 --dtype "float32" --save-every-n 10000 --valid-interval 20000
--model-name valle --share-embedding true --norm-first true --add-prenet false
--decoder-dim 256 --nhead 8 --num-decoder-layers 6 --prefix-mode 1
--base-lr 0.05 --warmup-steps 200 --average-period 0
--num-epochs 40 --start-epoch 3 --start-batch 0 --accumulate-grad-steps 4
--exp-dir exp/valle