diff --git a/examples/csmsc/tts2/README.md b/examples/csmsc/tts2/README.md index 7f7cdde0e..d852ef0c4 100644 --- a/examples/csmsc/tts2/README.md +++ b/examples/csmsc/tts2/README.md @@ -116,8 +116,10 @@ pwg_baker_ckpt_0.4 ``` `./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`. ```bash -CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} +CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} ``` +`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder. + ```text usage: synthesize.py [-h] [--am {speedyspeech_csmsc,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech,tacotron2_aishell3}] diff --git a/examples/csmsc/tts2/run.sh b/examples/csmsc/tts2/run.sh index 5732ea3c7..7cc126366 100755 --- a/examples/csmsc/tts2/run.sh +++ b/examples/csmsc/tts2/run.sh @@ -27,13 +27,13 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then fi if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then - # synthesize, vocoder is pwgan by default - CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 + # synthesize, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder + CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 fi if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then - # synthesize_e2e, vocoder is pwgan by default - CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 + # synthesize_e2e, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder + CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 fi if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then