From 6b48a206875771d37ec4581b534cf2613dd15c89 Mon Sep 17 00:00:00 2001
From: zxcd <228587199@qq.com>
Date: Thu, 27 Apr 2023 12:47:10 +0000
Subject: [PATCH 1/2] fix asr infer.py

---
 paddlespeech/cli/asr/infer.py     | 8 ++++----
 paddlespeech/cli/ssl/infer.py     | 2 +-
 paddlespeech/cli/whisper/infer.py | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/paddlespeech/cli/asr/infer.py b/paddlespeech/cli/asr/infer.py
index 7a7aef8b0e5..231a00f4d80 100644
--- a/paddlespeech/cli/asr/infer.py
+++ b/paddlespeech/cli/asr/infer.py
@@ -25,9 +25,6 @@
 import numpy as np
 import paddle
 import soundfile
-from paddlespeech.audio.transform.transformation import Transformation
-from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer
-from paddlespeech.s2t.utils.utility import UpdateConfig
 from yacs.config import CfgNode
 
 from ...utils.env import MODEL_HOME
@@ -37,6 +34,9 @@
 from ..utils import CLI_TIMER
 from ..utils import stats_wrapper
 from ..utils import timer_register
+from paddlespeech.audio.transform.transformation import Transformation
+from paddlespeech.s2t.frontend.featurizer.text_featurizer import TextFeaturizer
+from paddlespeech.s2t.utils.utility import UpdateConfig
 
 __all__ = ['ASRExecutor']
 
@@ -274,7 +274,7 @@ def preprocess(self, model_type: str, input: Union[str, os.PathLike]):
             # fbank
             audio = preprocessing(audio, **preprocess_args)
 
-            audio_len = paddle.to_tensor(audio.shape[0])
+            audio_len = paddle.to_tensor(audio.shape[0]).unsqueeze(axis=0)
             audio = paddle.to_tensor(audio, dtype='float32').unsqueeze(axis=0)
 
             self._inputs["audio"] = audio
diff --git a/paddlespeech/cli/ssl/infer.py b/paddlespeech/cli/ssl/infer.py
index dce7c77815d..44fbb425791 100644
--- a/paddlespeech/cli/ssl/infer.py
+++ b/paddlespeech/cli/ssl/infer.py
@@ -245,7 +245,7 @@ def preprocess(self, model_type: str, input: Union[str, os.PathLike]):
         # fbank
         audio = preprocessing(audio, **preprocess_args)
 
-        audio_len = paddle.to_tensor(audio.shape[0])
+        audio_len = paddle.to_tensor(audio.shape[0]).unsqueeze(axis=0)
         audio = paddle.to_tensor(audio, dtype='float32').unsqueeze(axis=0)
 
         self._inputs["audio"] = audio
diff --git a/paddlespeech/cli/whisper/infer.py b/paddlespeech/cli/whisper/infer.py
index ebcca890b59..17e8c0b8c9c 100644
--- a/paddlespeech/cli/whisper/infer.py
+++ b/paddlespeech/cli/whisper/infer.py
@@ -253,7 +253,7 @@ def preprocess(self, model_type: str, input: Union[str, os.PathLike]):
         # fbank
         audio = log_mel_spectrogram(audio, resource_path=self.resource_path)
 
-        audio_len = paddle.to_tensor(audio.shape[0])
+        audio_len = paddle.to_tensor(audio.shape[0]).unsqueeze(axis=0)
 
         self._inputs["audio"] = audio
         self._inputs["audio_len"] = audio_len

From c6a83b07754914c5f7af5192f9a5e3e4632a0402 Mon Sep 17 00:00:00 2001
From: zxcd <228587199@qq.com>
Date: Fri, 28 Apr 2023 03:21:13 +0000
Subject: [PATCH 2/2] add readme.

---
 README.md    | 1 +
 README_cn.md | 1 +
 2 files changed, 2 insertions(+)

diff --git a/README.md b/README.md
index 4f03f57459e..f9ae1ead7e7 100644
--- a/README.md
+++ b/README.md
@@ -178,6 +178,7 @@ Via the easy-to-use, efficient, flexible and scalable implementation, our vision
   - 🧩  *Cascaded models application*: as an extension of the typical traditional audio tasks, we combine the workflows of the aforementioned tasks with other fields like Natural language processing (NLP) and Computer Vision (CV).
 
 ### Recent Update
+- ⚡ 2023.04.28: Fix [0-d tensor](https://github.com/PaddlePaddle/PaddleSpeech/pull/3214), with the upgrade of paddlepaddle==2.5, the problem of modifying 0-d tensor has been solved.
 - 👑 2023.04.25: Add [AMP for U2 conformer](https://github.com/PaddlePaddle/PaddleSpeech/pull/3167).
 - 🔥 2023.04.06: Add [subtitle file (.srt format) generation example](./demos/streaming_asr_server).
 - 🔥 2023.03.14: Add SVS(Singing Voice Synthesis) examples with Opencpop dataset, including [DiffSinger](./examples/opencpop/svs1)、[PWGAN](./examples/opencpop/voc1) and [HiFiGAN](./examples/opencpop/voc5), the effect is continuously optimized.
diff --git a/README_cn.md b/README_cn.md
index e5e18f0c59e..25a716d2961 100644
--- a/README_cn.md
+++ b/README_cn.md
@@ -183,6 +183,7 @@
   - 🧩 级联模型应用: 作为传统语音任务的扩展，我们结合了自然语言处理、计算机视觉等任务，实现更接近实际需求的产业级应用。
 
 ### 近期更新
+- ⚡ 2023.04.28: 修正 [0-d tensor](https://github.com/PaddlePaddle/PaddleSpeech/pull/3214), 配合PaddlePaddle2.5升级修改了0-d tensor的问题。
 - 👑 2023.04.25: 新增 [U2 conformer 的 AMP 训练](https://github.com/PaddlePaddle/PaddleSpeech/pull/3167).
 - 👑 2023.04.06: 新增 [srt格式字幕生成功能](./demos/streaming_asr_server)。
 - 🔥 2023.03.14: 新增基于 Opencpop 数据集的 SVS (歌唱合成) 示例，包含 [DiffSinger](./examples/opencpop/svs1)、[PWGAN](./examples/opencpop/voc1) 和 [HiFiGAN](./examples/opencpop/voc5)，效果持续优化中。