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.
50 lines
1.6 KiB
50 lines
1.6 KiB
train_output_path=$1
|
|
|
|
stage=0
|
|
stop_stage=0
|
|
|
|
# e2e, synthesize from text
|
|
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
|
|
python3 ${BIN_DIR}/../ort_predict_e2e.py \
|
|
--inference_dir=${train_output_path}/inference_onnx \
|
|
--am=fastspeech2_canton \
|
|
--voc=pwgan_aishell3 \
|
|
--spk_id=10 \
|
|
--output_dir=${train_output_path}/onnx_infer_out_e2e \
|
|
--text=${BIN_DIR}/../sentences_canton.txt \
|
|
--phones_dict=dump/phone_id_map.txt \
|
|
--speaker_dict=dump/speaker_id_map.txt \
|
|
--lang=canton \
|
|
--device=cpu \
|
|
--cpu_threads=2
|
|
fi
|
|
|
|
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
|
|
python3 ${BIN_DIR}/../ort_predict_e2e.py \
|
|
--inference_dir=${train_output_path}/inference_onnx \
|
|
--am=fastspeech2_canton \
|
|
--voc=mb_melgan_csmsc \
|
|
--spk_id=10 \
|
|
--output_dir=${train_output_path}/onnx_infer_out_e2e \
|
|
--text=${BIN_DIR}/../sentences_canton.txt \
|
|
--phones_dict=dump/phone_id_map.txt \
|
|
--speaker_dict=dump/speaker_id_map.txt \
|
|
--lang=canton \
|
|
--device=cpu \
|
|
--cpu_threads=2
|
|
fi
|
|
|
|
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
|
|
python3 ${BIN_DIR}/../ort_predict_e2e.py \
|
|
--inference_dir=${train_output_path}/inference_onnx \
|
|
--am=fastspeech2_canton \
|
|
--voc=hifigan_csmsc \
|
|
--output_dir=${train_output_path}/onnx_infer_out_e2e \
|
|
--text=${BIN_DIR}/../sentences_canton.txt \
|
|
--phones_dict=dump/phone_id_map.txt \
|
|
--speaker_dict=dump/speaker_id_map.txt \
|
|
--lang=canton \
|
|
--device=cpu \
|
|
--cpu_threads=2
|
|
fi
|