fix typos and docs

examples/tacotron2_aishell3/aishell3.py

@@ -11,7 +11,7 @@ from preprocess_transcription import _phones, _tones
 voc_phones = Vocab(sorted(list(_phones)))
 print("vocab_phones:\n", voc_phones)
 voc_tones = Vocab(sorted(list(_tones)))
-print("vocab+tones:\n", voc_tones)
+print("vocab_tones:\n", voc_tones)
 
 
 class AiShell3(Dataset):

examples/tacotron2_aishell3/train.py

@@ -183,8 +183,8 @@ class Experiment(ExperimentBase):
                 config.training.weight_decay),
             grad_clip=grad_clip)
         criterion = Tacotron2Loss(
-            use_stop_token_loss=True,
-            use_guided_attention_loss=False,
+            use_stop_token_loss=config.model.use_stop_token,
+            use_guided_attention_loss=config.model.use_guided_attention_loss,
             sigma=config.model.guided_attention_loss_sigma)
         self.model = model
         self.optimizer = optimizer

parakeet/models/tacotron2.py

@@ -205,8 +205,8 @@ class Tacotron2Encoder(nn.Layer):
 
         Parameters
         ----------
-        x: Tensor [shape=(B, T)]
-            Batch of the sequencees of padded character ids.
+        x: Tensor [shape=(B, T, C)]
+            Input embeddings.
 
         text_lens: Tensor [shape=(B,)], optional
             Batch of lengths of each text input batch. Defaults to None.
@@ -502,7 +502,7 @@ class Tacotron2Decoder(nn.Layer):
                 if int(paddle.argmax(alignment[0])) == encoder_steps - 1:
                     if first_hit_end is None:
                         first_hit_end = i
-                    elif i > (first_hit_end + 10):
+                    elif i > (first_hit_end + 20):
                         print("content exhausted!")
                         break
             if len(mel_outputs) == max_decoder_steps: