update csmsc/tts3

examples/csmsc/tts3/README.md

@@ -106,10 +106,11 @@ pwg_baker_ckpt_0.4
 └── pwg_stats.npy                  # statistics used to normalize spectrogram when training parallel wavegan
 ```
 `./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`.
+
 ```bash
 CUDA_VISIBLE_DEVICES=${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.
+`--stage` controls the vocoder model during synthesis, which can be one of the following values: `0`, `1`, `2`, `3`, or `4`, representing the use of `pwgan`, `multi band melgan`, `style melgan`, `hifigan`, or `wavernn` model as vocoder respectively.
 
 ```text
 usage: synthesize.py [-h]
@@ -156,9 +157,12 @@ optional arguments:
                         output dir.
 ```
 `./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} ${ckpt_name}
+CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
 ```
+`--stage` controls the vocoder model during synthesis, which can be one of the following values: `0`, `1`,  `3`, or `4`, representing the use of `pwgan`, `multi band melgan`, `hifigan`, or `wavernn` model as vocoder respectively.
+
 ```text
 usage: synthesize_e2e.py [-h]
                          [--am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech}]

examples/csmsc/tts3/run.sh

@@ -27,12 +27,22 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
-    # synthesize, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder
+    # synthesize, vocoder is pwgan by default stage 0
+    # stage 1 will use multi band melgan as vocoder
+    # stage 2 will use style melgan as vocoder
+    # stage 3 will use hifigan as vocoder 
+    # stage 4 will use wavernn as vocoder 
+
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
-    # synthesize_e2e, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder
+    # synthesize_e2e, vocoder is pwgan by default stage 0
+    # stage 1 will use multi band melgan as vocoder
+    # stage 3 will use hifigan as vocoder
+    # stage 4 will use wavernn as vocoder
+
+
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi