Update asr and audio tagging demo.

demos/audio_tagging/README.md

@@ -7,7 +7,7 @@ This demo is an implementation to tag an audio file with 527 [AudioSet](https://
 
 ## Usage
 ### 1. Installation
-```sh
+```bash
 pip install paddlespeech
 ```
 
@@ -15,16 +15,20 @@ pip install paddlespeech
 Input of this demo should be a WAV file(`.wav`).
 
 Here are sample files for this demo that can be downloaded:
-```sh
+```bash
 wget https://paddlespeech.bj.bcebos.com/PaddleAudio/cat.wav https://paddlespeech.bj.bcebos.com/PaddleAudio/dog.wav
 ```
 
 ### 3. Usage
 - Command Line(Recommended)
-  ```sh
+  ```bash
   paddlespeech cls --input ~/cat.wav --topk 10
   ```
-  Command usage:
+  Usage:
+  ```bash
+  paddlespeech cls --help
+  ```
+  Arguments:
   - `input`(required): Audio file to tag.
   - `model`: Model type of tagging task. Default: `panns_cnn14`.
   - `config`: Config of tagging task. Use pretrained model when it is None. Default: `None`.
@@ -34,7 +38,7 @@ wget https://paddlespeech.bj.bcebos.com/PaddleAudio/cat.wav https://paddlespeech
   - `device`: Choose device to execute model inference. Default: default device of paddlepaddle in current environment.
 
   Output:
-  ```sh
+  ```bash
   [2021-12-08 14:49:40,671] [    INFO] [utils.py] [L225] - CLS Result:
   Cat: 0.8991316556930542
   Domestic animals, pets: 0.8806838393211365
@@ -49,11 +53,23 @@ wget https://paddlespeech.bj.bcebos.com/PaddleAudio/cat.wav https://paddlespeech
   ```
 
 - Python API
-  ```sh
-  python tag.py --input ~/cat.wav
+  ```bash
+  import paddle
+  from paddlespeech.cli import CLSExecutor
+
+  cls_executor = CLSExecutor()
+  result = cls_executor(
+      model_type='panns_cnn14',
+      cfg_path=None,  # Set `cfg_path` and `ckpt_path` to None to use pretrained model.
+      label_file=None,
+      ckpt_path=None,
+      audio_file='./cat.wav',
+      topk=10,
+      device=paddle.get_device(), )
+  print('CLS Result: \n{}'.format(result))
   ```
   Output:
-  ```sh
+  ```bash
   CLS Result:
   Cat: 0.8991316556930542
   Domestic animals, pets: 0.8806838393211365

demos/audio_tagging/tag.py

-# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-import argparse
-
-import paddle
-
-from paddlespeech.cli import CLSExecutor
-
-# yapf: disable
-parser = argparse.ArgumentParser()
-parser.add_argument(
-    '--input', type=str, required=True, help='Audio file to recognize.')
-args = parser.parse_args()
-# yapf: enable
-
-if __name__ == '__main__':
-    cls_executor = CLSExecutor()
-    result = cls_executor(
-        model_type='panns_cnn14',
-        cfg_path=None,  # Set `cfg_path` and `ckpt_path` to None to use pretrained model.
-        label_file=None,
-        ckpt_path=None,
-        audio_file=args.input,
-        topk=10,
-        device=paddle.get_device(), )
-    print('CLS Result: \n{}'.format(result))

demos/speech_recognition/README.md

@@ -7,7 +7,7 @@ This demo is an implementation to recognize text from a specific audio file. It
 
 ## Usage
 ### 1. Installation
-```sh
+```bash
 pip install paddlespeech
 ```
 
@@ -15,16 +15,20 @@ pip install paddlespeech
 Input of this demo should be a WAV file(`.wav`), and the sample rate must be same as the model's.
 
 Here are sample files for this demo that can be downloaded:
-```sh
+```bash
 wget https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav
 ```
 
 ### 3. Usage
 - Command Line(Recommended)
-  ```sh
+  ```bash
   paddlespeech asr --input ~/zh.wav
   ```
-  Command usage:
+  Usage:
+  ```bash
+  paddlespeech asr --help
+  ```
+  Arguments:
   - `input`(required): Audio file to recognize.
   - `model`: Model type of asr task. Default: `conformer_wenetspeech`.
   - `lang`: Model language. Default: `zh`.
@@ -34,16 +38,29 @@ wget https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespeech.
   - `device`: Choose device to execute model inference. Default: default device of paddlepaddle in current environment.
 
   Output:
-  ```sh
+  ```bash
   [2021-12-08 13:12:34,063] [    INFO] [utils.py] [L225] - ASR Result: 我认为跑步最重要的就是给我带来了身体健康
   ```
 
 - Python API
-  ```sh
-  python asr.py --input ~/zh.wav
+  ```python
+  import paddle
+  from paddlespeech.cli import ASRExecutor
+
+  asr_executor = ASRExecutor()
+  text = asr_executor(
+      model='conformer_wenetspeech',
+      lang='zh',
+      sample_rate=16000,
+      config=None,  # Set `conf` and `ckpt_path` to None to use pretrained model.
+      ckpt_path=None,
+      audio_file='./zh.wav',
+      device=paddle.get_device())
+  print('ASR Result: \n{}'.format(text))
   ```
+
   Output:
-  ```sh
+  ```bash
   ASR Result:
   我认为跑步最重要的就是给我带来了身体健康
   ```

demos/speech_recognition/asr.py

-# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-import argparse
-
-import paddle
-
-from paddlespeech.cli import ASRExecutor
-
-# yapf: disable
-parser = argparse.ArgumentParser()
-parser.add_argument(
-    '--input', type=str, required=True, help='Audio file to recognize.')
-args = parser.parse_args()
-# yapf: enable
-
-if __name__ == '__main__':
-    asr_executor = ASRExecutor()
-    text = asr_executor(
-        model='conformer_wenetspeech',
-        lang='zh',
-        sample_rate=16000,
-        config=None,  # Set `conf` and `ckpt_path` to None to use pretrained model.
-        ckpt_path=None,
-        audio_file=args.input,
-        device=paddle.get_device(), )
-    print('ASR Result: \n{}'.format(text))