NUM8

examples/csmsc/tts2/README.md

@@ -116,7 +116,11 @@ 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} ${ckpt_name}
+`./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`. 
+
+CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
+
+`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder.
 ```
 ```text
 usage: synthesize.py [-h]
@@ -164,7 +168,11 @@ optional arguments:
 ```
 `./local/synthesize_e2e.sh` calls `${BIN_DIR}/../synthesize_e2e.py`, which can synthesize waveform from text file.
 ```bash
-CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name}
+`./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`. 
+
+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_e2e.py [-h]

examples/csmsc/tts2/run.sh

@@ -27,13 +27,13 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
-    # synthesize, vocoder is pwgan by default
+    # synthesize, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
-    # synthesize_e2e, vocoder is pwgan by default
+    # synthesize_e2e, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+    CUDA_VISIBLE_DEVICES=${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