mechanicalsea

/

speecht5-sid

like 5

Hi, Thanks for you attention. We release the scripts of the SID inference at SpeechT5 SID.
For example:

CHECKPOINT_PATH=
DATA_ROOT=
SUBSET=
USER_DIR=
RESULTS_PATH=

mkdir -p ${RESULTS_PATH}

python scripts/generate_class.py ${DATA_ROOT} --gen-subset ${SUBSET} --user-dir ${USER_DIR} \
  --log-format json --task speecht5 --results-path ${RESULTS_PATH} --path ${CHECKPOINT_PATH} \
  --t5-task s2c --batch-size 1 --max-speech-positions 8000 --sample-rate 16000

In fact, generate_class.py implement the inference of the fine tuned model.
Wish it helpful.