diff --git a/examples/csmsc/tts0/README.md b/examples/csmsc/tts0/README.md
index ce682495e97..e471ec95032 100644
--- a/examples/csmsc/tts0/README.md
+++ b/examples/csmsc/tts0/README.md
@@ -5,6 +5,17 @@ This example contains code used to train a [Tacotron2](https://arxiv.org/abs/171
 ### Download and Extract
 Download CSMSC from it's [Official Website](https://test.data-baker.com/data/index/TNtts/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
 
+The structure of the folder is listed below.
+
+```text
+└─ Wave
+    └─ .wav files (audio speech)
+└─ PhoneLabeling
+    └─ .interval files (alignment between phoneme and duration)
+└─ ProsodyLabeling
+   └─ 000001-010000.txt (text with prosodic by pinyin)
+```
+
 ### Get MFA Result and Extract
 We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes for Tacotron2, the durations of MFA are not needed here.
 You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
diff --git a/paddlespeech/t2s/modules/tacotron2/attentions.py b/paddlespeech/t2s/modules/tacotron2/attentions.py
index 5d1a2484536..86407e7786e 100644
--- a/paddlespeech/t2s/modules/tacotron2/attentions.py
+++ b/paddlespeech/t2s/modules/tacotron2/attentions.py
@@ -171,7 +171,8 @@ def forward(
         if paddle.sum(att_prev) == 0:
             # if no bias, 0 0-pad goes 0
             att_prev = 1.0 - make_pad_mask(enc_hs_len)
-            att_prev = att_prev / enc_hs_len.unsqueeze(-1)
+            att_prev = att_prev / enc_hs_len.unsqueeze(-1).astype(
+                att_prev.dtype)
 
         # att_prev: (utt, frame) -> (utt, 1, 1, frame)
         # -> (utt, att_conv_chans, 1, frame)
diff --git a/paddlespeech/t2s/modules/tacotron2/encoder.py b/paddlespeech/t2s/modules/tacotron2/encoder.py
index 224c82400d2..ac942be0f13 100644
--- a/paddlespeech/t2s/modules/tacotron2/encoder.py
+++ b/paddlespeech/t2s/modules/tacotron2/encoder.py
@@ -162,6 +162,9 @@ def forward(self, xs, ilens=None):
             return xs.transpose([0, 2, 1])
         if not isinstance(ilens, paddle.Tensor):
             ilens = paddle.to_tensor(ilens)
+        # check if ilens is 0-dim tensor, if so, add a dimension
+        if ilens.ndim == 0:
+            ilens = ilens.unsqueeze(0)
         xs = xs.transpose([0, 2, 1])
         # for dygraph to static graph
         # self.blstm.flatten_parameters()