Merge pull request #2107 from yt605155624/rm_more_log

[cli]rm extra log

paddlespeech/cli/executor.py

@@ -217,7 +217,7 @@ class BaseExecutor(ABC):
             logging.getLogger(name) for name in logging.root.manager.loggerDict
         ]
         for l in loggers:
-            l.disabled = True
+            l.setLevel(logging.ERROR)
 
     def show_rtf(self, info: Dict[str, List[float]]):
         """

paddlespeech/cli/tts/infer.py

@@ -267,21 +267,18 @@ class TTSExecutor(BaseExecutor):
         with open(self.phones_dict, "r") as f:
             phn_id = [line.strip().split() for line in f.readlines()]
         vocab_size = len(phn_id)
-        print("vocab_size:", vocab_size)
 
         tone_size = None
         if self.tones_dict:
             with open(self.tones_dict, "r") as f:
                 tone_id = [line.strip().split() for line in f.readlines()]
             tone_size = len(tone_id)
-            print("tone_size:", tone_size)
 
         spk_num = None
         if self.speaker_dict:
             with open(self.speaker_dict, 'rt') as f:
                 spk_id = [line.strip().split() for line in f.readlines()]
             spk_num = len(spk_id)
-            print("spk_num:", spk_num)
 
         # frontend
         if lang == 'zh':
@@ -291,7 +288,6 @@ class TTSExecutor(BaseExecutor):
 
         elif lang == 'en':
             self.frontend = English(phone_vocab_path=self.phones_dict)
-        print("frontend done!")
 
         # acoustic model
         odim = self.am_config.n_mels
@@ -324,7 +320,6 @@ class TTSExecutor(BaseExecutor):
         am_normalizer = ZScore(am_mu, am_std)
         self.am_inference = am_inference_class(am_normalizer, am)
         self.am_inference.eval()
-        print("acoustic model done!")
 
         # vocoder
         # model: {model_name}_{dataset}
@@ -347,7 +342,6 @@ class TTSExecutor(BaseExecutor):
         voc_normalizer = ZScore(voc_mu, voc_std)
         self.voc_inference = voc_inference_class(voc_normalizer, voc)
         self.voc_inference.eval()
-        print("voc done!")
 
     def preprocess(self, input: Any, *args, **kwargs):
         """

paddlespeech/t2s/models/fastspeech2/fastspeech2.py

@@ -258,7 +258,6 @@ class FastSpeech2(nn.Layer):
             padding_idx=self.padding_idx)
 
         if encoder_type == "transformer":
-            print("encoder_type is transformer")
             self.encoder = TransformerEncoder(
                 idim=idim,
                 attention_dim=adim,
@@ -275,7 +274,6 @@ class FastSpeech2(nn.Layer):
                 positionwise_layer_type=positionwise_layer_type,
                 positionwise_conv_kernel_size=positionwise_conv_kernel_size, )
         elif encoder_type == "conformer":
-            print("encoder_type is conformer")
             self.encoder = ConformerEncoder(
                 idim=idim,
                 attention_dim=adim,
@@ -362,7 +360,6 @@ class FastSpeech2(nn.Layer):
         # NOTE: we use encoder as decoder
         # because fastspeech's decoder is the same as encoder
         if decoder_type == "transformer":
-            print("decoder_type is transformer")
             self.decoder = TransformerEncoder(
                 idim=0,
                 attention_dim=adim,
@@ -380,7 +377,6 @@ class FastSpeech2(nn.Layer):
                 positionwise_layer_type=positionwise_layer_type,
                 positionwise_conv_kernel_size=positionwise_conv_kernel_size, )
         elif decoder_type == "conformer":
-            print("decoder_type is conformer")
             self.decoder = ConformerEncoder(
                 idim=0,
                 attention_dim=adim,