Added Text Rhythm Prediction, test=tts

examples/other/rhy/README.md

@@ -22,7 +22,7 @@ The pretrained model can be downloaded here:
 
 [ernie-1.0_aishellcsmsc_ckpt_1.3.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/rhy_predict/ernie-1.0_aishellcsmsc_ckpt_1.3.0.zip)
 
-And you should put it into `exp/YOUREXP/checkpoints` folder.
+And you should put it into `exp/${YOUREXP}/checkpoints` folder.
 
 ## Rhythm mapping
 Four punctuation marks are used to denote the rhythm marks respectively:

examples/other/rhy/run.sh

@@ -11,7 +11,7 @@ csmsc_data=000001-010000.txt
 processed_path=data
 
 conf_path=conf/default.yaml
-train_output_path=exp/rhy
+train_output_path=exp/default
 ckpt_name=snapshot_iter_2600.pdz
 text=我们城市的复苏有赖于他强有力的政策。
 print_eval=false

paddlespeech/text/exps/ernie_linear/test.py

@@ -97,8 +97,6 @@ def test(args):
         t2 = evaluation(test_total_label, test_total_predict)
         print('=========================================================')
         print(t2)
-    else:
-        pass
 
 
 def main():
@@ -109,7 +107,7 @@ def main():
     parser.add_argument(
         "--print_eval",
         type=str2bool,
-        default=False)
+        default=True)
     parser.add_argument(
         "--ngpu", type=int, default=1, help="if ngpu=0, use cpu.")