[cherry-pick][r1.1] fix g2pw input type for windows (#2289)

* [TTS]指定G2PW的传入数据类型 , test=tts (#2288)

* fix ONNXRuntimeError Specify data type (int64),test=tts

* Tactron2→Tacotron2 ,test=doc

* update version
Co-authored-by: N李子 <54951765+kslz@users.noreply.github.com>

docs/source/released_model.md

@@ -67,7 +67,7 @@ WaveRNN | CSMSC |[WaveRNN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tr
 Model Type | Dataset| Example Link | Pretrained Models
 :-------------:| :------------:| :-----: | :-----: | 
 GE2E| AISHELL-3, etc. |[ge2e](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/ge2e)|[ge2e_ckpt_0.3.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/ge2e/ge2e_ckpt_0.3.zip)
-GE2E + Tactron2| AISHELL-3 |[ge2e-tactron2-aishell3](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/vc0)|[tacotron2_aishell3_ckpt_vc0_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/tacotron2/tacotron2_aishell3_ckpt_vc0_0.2.0.zip)
+GE2E + Tacotron2| AISHELL-3 |[ge2e-Tacotron2-aishell3](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/vc0)|[tacotron2_aishell3_ckpt_vc0_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/tacotron2/tacotron2_aishell3_ckpt_vc0_0.2.0.zip)
 GE2E + FastSpeech2 | AISHELL-3  |[ge2e-fastspeech2-aishell3](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/vc1)|[fastspeech2_nosil_aishell3_vc1_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_aishell3_vc1_ckpt_0.5.zip)
 
 

docs/source/tts/quick_start.md

@@ -7,7 +7,7 @@ The examples in PaddleSpeech are mainly classified by datasets, the TTS datasets
 * VCTK (English multiple speakers)
 
 The models in PaddleSpeech TTS have the following mapping relationship:
-* tts0 - Tactron2
+* tts0 - Tacotron2
 * tts1 - TransformerTTS
 * tts2 - SpeedySpeech
 * tts3 - FastSpeech2
@@ -17,7 +17,7 @@ The models in PaddleSpeech TTS have the following mapping relationship:
 * voc3 - MultiBand MelGAN
 * voc4 - Style MelGAN
 * voc5 - HiFiGAN
-* vc0 - Tactron2 Voice Clone with GE2E
+* vc0 - Tacotron2 Voice Clone with GE2E
 * vc1 - FastSpeech2 Voice Clone with GE2E
 
 ## Quick Start

docs/source/tts/quick_start_cn.md

@@ -9,7 +9,7 @@
 
 PaddleSpeech 的 TTS 模型具有以下映射关系：
 
-* tts0 - Tactron2
+* tts0 - Tacotron2
 * tts1 - TransformerTTS
 * tts2 - SpeedySpeech
 * tts3 - FastSpeech2
@@ -19,7 +19,7 @@ PaddleSpeech 的 TTS 模型具有以下映射关系：
 * voc3 - MultiBand MelGAN
 * voc4 - Style MelGAN
 * voc5 - HiFiGAN
-* vc0 - Tactron2 Voice Clone with GE2E
+* vc0 - Tacotron2 Voice Clone with GE2E
 * vc1 - FastSpeech2 Voice Clone with GE2E
 
 ## 快速开始

docs/tutorial/tts/tts_tutorial.ipynb

@@ -769,7 +769,7 @@
     "```\n",
     "我们在每个数据集的 README.md 介绍了子目录和模型的对应关系, 在 TTS 中有如下对应关系:\n",
     "```text\n",
-    "tts0 - Tactron2\n",
+    "tts0 - Tacotron2\n",
     "tts1 - TransformerTTS\n",
     "tts2 - SpeedySpeech\n",
     "tts3 - FastSpeech2\n",

examples/aishell3/README.md

 # Aishell3
 
-* tts0 - Tactron2
+* tts0 - Tacotron2
 * tts1 - TransformerTTS
 * tts2 - SpeedySpeech
 * tts3 - FastSpeech2
@@ -8,5 +8,5 @@
 * voc1 - Parallel WaveGAN
 * voc2 - MelGAN
 * voc3 - MultiBand MelGAN
-* vc0 - Tactron2 Voice Cloning with GE2E
+* vc0 - Tacotron2 Voice Cloning with GE2E
 * vc1 - FastSpeech2 Voice Cloning with GE2E

examples/csmsc/README.md

 
 # CSMSC
 
-* tts0 - Tactron2
+* tts0 - Tacotron2
 * tts1 - TransformerTTS
 * tts2 - SpeedySpeech
 * tts3 - FastSpeech2

examples/ljspeech/README.md

 
 # LJSpeech
 
-* tts0 - Tactron2
+* tts0 - Tacotron2
 * tts1 - TransformerTTS
 * tts2 - SpeedySpeech
 * tts3 - FastSpeech2

examples/vctk/README.md

 
 # VCTK
 
-* tts0 - Tactron2
+* tts0 - Tacotron2
 * tts1 - TransformerTTS
 * tts2 - SpeedySpeech
 * tts3 - FastSpeech2

paddlespeech/t2s/frontend/g2pw/dataset.py

@@ -81,12 +81,12 @@ def prepare_onnx_input(tokenizer,
         position_ids.append(position_id)
 
     outputs = {
-        'input_ids': np.array(input_ids),
-        'token_type_ids': np.array(token_type_ids),
-        'attention_masks': np.array(attention_masks),
+        'input_ids': np.array(input_ids).astype(np.int64),
+        'token_type_ids': np.array(token_type_ids).astype(np.int64),
+        'attention_masks': np.array(attention_masks).astype(np.int64),
         'phoneme_masks': np.array(phoneme_masks).astype(np.float32),
-        'char_ids': np.array(char_ids),
-        'position_ids': np.array(position_ids),
+        'char_ids': np.array(char_ids).astype(np.int64),
+        'position_ids': np.array(position_ids).astype(np.int64),
     }
     return outputs
 

setup.py

@@ -28,7 +28,7 @@ from setuptools.command.test import test
 
 HERE = Path(os.path.abspath(os.path.dirname(__file__)))
 
-VERSION = '1.1.1'
+VERSION = '1.1.2'
 COMMITID = 'none'
 
 base = [