update examples/csmsc/README.md and examples/csmsc/{tts0,tts2,tts3}

examples/csmsc/tts0/README.md

@@ -101,7 +101,7 @@ pwg_baker_ckpt_0.4
 ```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` or `2` or `3`, use `pwgan` or `multi band melgan` or `style melgan` or `hifigan`model as vocoder.
+`--stage` controls the vocoder model during synthesis, which can use stage `0-4` to select the vocoder to use {`pwgan`, `multi band melgan`,  `style melgan`, ` hifigan`,  `wavernn`}
 
 ```text
 usage: synthesize.py [-h]
@@ -152,7 +152,7 @@ optional arguments:
 ```bash
 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 `0` or `1` or `3` or `4`, use `pwgan` or `multi band melgan` or `hifigan` or `wavernn`model as vocoder.
+`--stage` controls the vocoder model during synthesis, which can use stage `0,1,3,4` to select the vocoder to use{`pwgan`, `multi band melgan`,  `hifigan`,  `wavernn`}
 
 ```text
 usage: synthesize_e2e.py [-h]

examples/csmsc/tts0/run.sh

@@ -28,17 +28,13 @@ fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
     # synthesize, vocoder is pwgan by default stage 0
-    # stage 1 will use multi band melgan as vocoder
-    # stage 2 will use style melgan as vocoder
-    # stage 3 will use hifigan as vocoer
+    # stage 1-4 to select the vocoder to use {multi band melgan, style melgan, hifigan, wavernn}
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
     # synthesize_e2e, vocoder is pwgan by default stage 0
-    # stage 1 will use multi band melgan as vocoder
-    # stage 3 will use  hifigan as vocoder
-    # stage 4 will use wavernn as vocoder
+    # stage 1,3,4 to select the vocoder to use {multi band melgan, hifigan, wavernn}
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi
 

examples/csmsc/tts2/README.md

@@ -118,7 +118,7 @@ pwg_baker_ckpt_0.4
 ```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 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.
+`--stage` controls the vocoder model during synthesis, which can use stage `0-4` to select the vocoder to use {`pwgan`, `multi band melgan`, `style melgan`, `hifigan`, `wavernn`}
 
 ```text
 usage: synthesize.py [-h]
@@ -165,10 +165,11 @@ 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 --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.
+`--stage` controls the vocoder model during synthesis, which can use stage `0,1,3,4` to select the vocoder to use {`pwgan`, `multi band melgan`, `hifigan`, `wavernn`}
 
 ```text
 usage: synthesize_e2e.py [-h]

examples/csmsc/tts2/run.sh

@@ -28,18 +28,13 @@ fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
     # synthesize, vocoder is pwgan by default stage 0
-    # stage 1 will use multi band melgan as vocoder
-    # stage 2 will use style melgan as vocoder
-    # stage 3 will use hifigan as vocoder
-    # stage 4 will use wavernn as vocoder
+    # use stage 1-4 to select the vocoder to use {multi band melgan, style melgan, hifigan, wavernn}
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
     # synthesize_e2e, vocoder is pwgan by default stage 0
-    # stage 1 will use multi band melgan as vocoder
-    # stage 3 will use hifigan as vocoder
-    # stage 4 will use wavernn as vocoder
+    # use stage 1,3,4 to select the vocoder to use {multi band melgan, hifigan, wavernn}
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi
 

examples/csmsc/tts3/README.md

@@ -110,7 +110,7 @@ pwg_baker_ckpt_0.4
 ```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 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.
+`--stage` controls the vocoder model during synthesis, which can use stage `0-4` to select the vocoder to use {`pwgan`, `multi band melgan`, `style melgan`, `hifigan`, `wavernn`}
 
 ```text
 usage: synthesize.py [-h]
@@ -161,7 +161,7 @@ optional arguments:
 ```bash
 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.
+`--stage` controls the vocoder model during synthesis, which can use stage `0,1,3,4` to select the vocoder to use {`pwgan`, `multi band melgan`, `hifigan`, `wavernn`}
 
 ```text
 usage: synthesize_e2e.py [-h]

examples/csmsc/tts3/run.sh

@@ -28,21 +28,13 @@ fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
     # synthesize, vocoder is pwgan by default stage 0
-    # stage 1 will use multi band melgan as vocoder
-    # stage 2 will use style melgan as vocoder
-    # stage 3 will use hifigan as vocoder 
-    # stage 4 will use wavernn as vocoder 
-
+    # use stage 1-4 to select the vocoder to use {multi band melgan, style melgan, hifigan, wavernn}
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
     # synthesize_e2e, vocoder is pwgan by default stage 0
-    # stage 1 will use multi band melgan as vocoder
-    # stage 3 will use hifigan as vocoder
-    # stage 4 will use wavernn as vocoder
-
-
+    # use stage 1,3,4 to select the vocoder to use {multi band melgan, hifigan, wavernn}
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi
 

examples/csmsc/tts3_rhy/README.md

@@ -20,7 +20,7 @@ Run the command below to
 3. train the model.
 4. synthesize wavs.
     - synthesize waveform from `metadata.jsonl`.
-    - select vocoder type via `--stage` (0 = pwgan, 1 = multi band melgan, 3 = hifigan, 4 = wavernn)
+    - use stage `1,3,4` to select the vocoder to use {`multi band melgan`, `hifigan`, `wavernn`}
     - synthesize waveform from a text file.
 5. inference using the static model.
 ```bash

examples/csmsc/tts3_rhy/run.sh

@@ -34,8 +34,6 @@ fi
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
     # synthesize_e2e, vocoder is pwgan by default stage 0
-    # stage 1 will use multi band melgan as vocoder
-    # stage 3 will use hifigan as vocoder
-    # stage 4 will use wavernn as vocoder 
+    # use stage 1,3,4 to select the vocoder to use {multi band melgan, hifigan, wavernn}
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi