You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
54 lines
1.9 KiB
54 lines
1.9 KiB
#!/bin/bash
|
|
|
|
config_path=$1
|
|
train_output_path=$2
|
|
ckpt_name=$3
|
|
|
|
stage=0
|
|
stop_stage=0
|
|
|
|
# pwgan
|
|
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
|
|
FLAGS_allocator_strategy=naive_best_fit \
|
|
FLAGS_fraction_of_gpu_memory_to_use=0.01 \
|
|
python3 ${BIN_DIR}/../synthesize_e2e.py \
|
|
--am=fastspeech2_canton \
|
|
--am_config=${config_path} \
|
|
--am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
|
|
--am_stat=dump/train/speech_stats.npy \
|
|
--voc=pwgan_aishell3 \
|
|
--voc_config=pwg_aishell3_ckpt_0.5/default.yaml \
|
|
--voc_ckpt=pwg_aishell3_ckpt_0.5/snapshot_iter_1000000.pdz \
|
|
--voc_stat=pwg_aishell3_ckpt_0.5/feats_stats.npy \
|
|
--lang=canton \
|
|
--text=${BIN_DIR}/../../assets/sentences_canton.txt \
|
|
--output_dir=${train_output_path}/test_e2e \
|
|
--phones_dict=dump/phone_id_map.txt \
|
|
--speaker_dict=dump/speaker_id_map.txt \
|
|
--spk_id=10 \
|
|
--inference_dir=${train_output_path}/inference
|
|
fi
|
|
|
|
# hifigan
|
|
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
|
|
echo "in hifigan syn_e2e"
|
|
FLAGS_allocator_strategy=naive_best_fit \
|
|
FLAGS_fraction_of_gpu_memory_to_use=0.01 \
|
|
python3 ${BIN_DIR}/../synthesize_e2e.py \
|
|
--am=fastspeech2_canton \
|
|
--am_config=${config_path} \
|
|
--am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
|
|
--am_stat=dump/train/speech_stats.npy \
|
|
--voc=hifigan_aishell3 \
|
|
--voc_config=hifigan_aishell3_ckpt_0.2.0/default.yaml \
|
|
--voc_ckpt=hifigan_aishell3_ckpt_0.2.0/snapshot_iter_2500000.pdz \
|
|
--voc_stat=hifigan_aishell3_ckpt_0.2.0/feats_stats.npy \
|
|
--lang=canton \
|
|
--text=${BIN_DIR}/../../assets/sentences_canton.txt \
|
|
--output_dir=${train_output_path}/test_e2e \
|
|
--phones_dict=dump/phone_id_map.txt \
|
|
--speaker_dict=dump/speaker_id_map.txt \
|
|
--spk_id=10 \
|
|
--inference_dir=${train_output_path}/inference
|
|
fi
|