msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity

update the paddlespeech_client asr_online cli, test=doc

Browse Source
pull/1818/head
xiongxinlei 3 years ago
parent 7eb3ab0dfa
commit 9ca4f251cc
5 changed files with 295 additions and 10 deletions
Show Stats Download Patch File Download Diff File

8
demos/streaming_asr_server/README.md
Unescape View File

@ -186,16 +186,19 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
### 4. ASR Client Usage
#### 4.2 使用 `paddlespeech_client asr_online`
**Note:** The response time will be slightly longer when using the client for the first time
- Command Line (Recommended)
```
# if we use paddlespeech_client asr, we must specify the protocol to websocket
paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input ./zh.wav --protocol websocket
```
Usage:
```bash
paddlespeech_client asr_online --help
paddlespeech_client asr help
```
Arguments:
- `server_ip`: server ip. Default: 127.0.0.1
@ -204,6 +207,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
- `sample_rate`: Audio ampling rate, default: 16000.
- `lang`: Language. Default: "zh_cn".
- `audio_format`: Audio format. Default: "wav".
- `protocol`: protocol between client and server. Streaming asr must be websocket.
- `punc.server_ip`: punctuation server ip. Default: None.
- `punc.server_port`: punctuation server port. Default: None.
Output:
```bash

202
demos/streaming_asr_server/README_cn.md
Unescape View File

@ -5,18 +5,27 @@
## 介绍
这个demo是一个启动流式语音服务和访问服务的实现。 它可以通过使用`paddlespeech_server` 和 `paddlespeech_client`的单个命令或 python 的几行代码来实现。
流式语音识别服务只支持 `weboscket` 协议，不支持 `http` 协议。
**流式语音识别服务只支持 `weboscket` 协议，不支持 `http` 协议。**
## 使用方法
### 1. 安装
请看 [安装文档](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md).
安装 PaddleSpeech 的详细过程请看 [安装文档](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md)。
推荐使用 **paddlepaddle 2.2.1** 或以上版本。
你可以从medium，hard 二中方式中选择一种方式安装 PaddleSpeech。
你可以从medium，hard 两中方式中选择一种方式安装 PaddleSpeech。
### 2. 准备配置文件
配置文件可参见 `conf/ws_application.yaml` 和 `conf/ws_conformer_application.yaml` 。
流式ASR的服务启动脚本和服务测试脚本存放在 `PaddleSpeech/demos/streaming_asr_server` 目录。
下载好 `PaddleSpeech` 之后，进入到 `PaddleSpeech/demos/streaming_asr_server` 目录。
配置文件可参见该目录下 `conf/ws_application.yaml` 和 `conf/ws_conformer_application.yaml` 。
目前服务集成的模型有： DeepSpeech2和 conformer模型，对应的配置文件如下：
* DeepSpeech: `conf/ws_application.yaml`
* conformer: `conf/ws_conformer_application.yaml`
目前服务集成的模型有： DeepSpeech2和conformer模型。
@ -185,17 +194,197 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
```
### 4. ASR 客户端使用方法
#### 4.1 使用`paddlespeech_client asr `
**注意：** 初次使用客户端时响应时间会略长
- 命令行 (推荐使用)
```
# 使用 paddlespecch_asr 需要指定传入协议为 websocket
paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input ./zh.wav --protocol websocket
```
使用帮助:
```bash
paddlespeech_client asr help
```
参数:
- `server_ip`: 服务端ip地址，默认: 127.0.0.1。
- `port`: 服务端口，默认: 8090。
- `input`(必须输入): 用于识别的音频文件。
- `sample_rate`: 音频采样率，默认值：16000。
- `lang`: 模型语言，默认值：zh_cn。
- `audio_format`: 音频格式，默认值：wav。
- `protocol` 指定客户端和服务端之间服务的协议。在流式识别中必须指定 websocket。
- `punc.server_ip` 标点预测服务的ip。默认是None。
- `punc.server_port` 标点预测服务的端口port。默认是None。
输出:
```bash
[2022-04-21 15:59:03,904] [ INFO] - receive msg={"status": "ok", "signal": "server_ready"}
[2022-04-21 15:59:03,960] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:03,973] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:03,987] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,000] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,012] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,024] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,036] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,047] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,607] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,620] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,633] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,645] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,657] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,669] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,680] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:05,176] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,185] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,192] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,200] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,208] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,216] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,224] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,232] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,724] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,732] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,740] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,747] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,755] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,763] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,770] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:06,271] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,279] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,287] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,294] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,302] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,310] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,318] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,326] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,833] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,842] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,850] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,858] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,866] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,874] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,882] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:07,400] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,408] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,416] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,424] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,432] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,440] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,447] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,455] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,984] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:07,992] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:08,001] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:08,008] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:08,016] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:08,024] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:12,883] [ INFO] - final receive msg={'status': 'ok', 'signal': 'finished', 'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:12,884] [ INFO] - 我认为跑步最重要的就是给我带来了身体健康
[2022-04-21 15:59:12,884] [ INFO] - Response time 9.051567 s.
```
- Python API
```python
from paddlespeech.server.bin.paddlespeech_client import ASRClientExecutor
import json
asrclient_executor = ASRClientExecutor()
res = asrclient_executor(
input="./zh.wav",
server_ip="127.0.0.1",
port=8090,
sample_rate=16000,
lang="zh_cn",
audio_format="wav",
protocol="websocket")
print(res)
```
输出:
```bash
[2022-04-21 15:59:03,904] [ INFO] - receive msg={"status": "ok", "signal": "server_ready"}
[2022-04-21 15:59:03,960] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:03,973] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:03,987] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,000] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,012] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,024] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,036] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,047] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,607] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,620] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,633] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,645] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,657] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,669] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:04,680] [ INFO] - receive msg={'asr_results': ''}
[2022-04-21 15:59:05,176] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,185] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,192] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,200] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,208] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,216] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,224] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,232] [ INFO] - receive msg={'asr_results': '我认为跑'}
[2022-04-21 15:59:05,724] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,732] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,740] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,747] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,755] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,763] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:05,770] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'}
[2022-04-21 15:59:06,271] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,279] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,287] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,294] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,302] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,310] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,318] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,326] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'}
[2022-04-21 15:59:06,833] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,842] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,850] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,858] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,866] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,874] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:06,882] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'}
[2022-04-21 15:59:07,400] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,408] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,416] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,424] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,432] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,440] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,447] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,455] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'}
[2022-04-21 15:59:07,984] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:07,992] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:08,001] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:08,008] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:08,016] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:08,024] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:12,883] [ INFO] - final receive msg={'status': 'ok', 'signal': 'finished', 'asr_results': '我认为跑步最重要的就是给我带来了身体健康'}
[2022-04-21 15:59:12,884] [ INFO] - 我认为跑步最重要的就是给我带来了身体健康
```
#### 4.2 使用 `paddlespeech_client asr_online`
**注意：** 初次使用客户端时响应时间会略长
- 命令行 (推荐使用)
```
# 使用 paddlespecch_asr 需要指定传入协议为 websocket
paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8090 --input ./zh.wav
```
使用帮助:
```bash
paddlespeech_client asr_online --help
paddlespeech_client asr help
```
参数:
@ -205,6 +394,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
- `sample_rate`: 音频采样率，默认值：16000。
- `lang`: 模型语言，默认值：zh_cn。
- `audio_format`: 音频格式，默认值：wav。
- `protocol` 指定客户端和服务端之间服务的协议。在流式识别中必须指定 websocket。
- `punc.server_ip` 标点预测服务的ip。默认是None。
- `punc.server_port` 标点预测服务的端口port。默认是None。
输出:

2
examples/voxceleb/sv0/README.md
Unescape View File

@ -146,6 +146,6 @@ tar -xvf sv0_ecapa_tdnn_voxceleb12_ckpt_0_2_0.tar.gz
source path.sh
# If you have processed the data and get the manifest file， you can skip the following 2 steps
CUDA_VISIBLE_DEVICES= ./local/test.sh ./data sv0_ecapa_tdnn_voxceleb12_ckpt_0_1_2 conf/ecapa_tdnn.yaml
CUDA_VISIBLE_DEVICES= bash ./local/test.sh ./data sv0_ecapa_tdnn_voxceleb12_ckpt_0_1_2/model/ conf/ecapa_tdnn.yaml
```
The performance of the released models are shown in [this](./RESULTS.md)

18
examples/voxceleb/sv0/local/test.sh
Unescape View File

@ -33,10 +33,26 @@ dir=$1
exp_dir=$2
conf_path=$3
# get the gpu nums for training
ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
echo "using $ngpu gpus..."
# setting training device
device="cpu"
if ${use_gpu}; then
device="gpu"
fi
if [ $ngpu -le 0 ]; then
echo "no gpu, training in cpu mode"
device='cpu'
use_gpu=false
fi
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
# test the model and compute the eer metrics
python3 ${BIN_DIR}/test.py \
--data-dir ${dir} \
--load-checkpoint ${exp_dir} \
--config ${conf_path}
--config ${conf_path} \
--device ${device}
fi

75
paddlespeech/server/bin/paddlespeech_client.py
Unescape View File

@ -35,7 +35,7 @@ from paddlespeech.server.utils.util import wav2base64
__all__ = [
'TTSClientExecutor', 'TTSOnlineClientExecutor', 'ASRClientExecutor',
'CLSClientExecutor'
'ASROnlineClientExecutor', 'CLSClientExecutor'
]
@ -397,6 +397,77 @@ class ASRClientExecutor(BaseExecutor):
return res
@cli_client_register(
name='paddlespeech_client.asr_online',
description='visit asr online service')
class ASROnlineClientExecutor(BaseExecutor):
def __init__(self):
super(ASROnlineClientExecutor, self).__init__()
self.parser = argparse.ArgumentParser(
prog='paddlespeech_client.asr_online', add_help=True)
self.parser.add_argument(
'--server_ip', type=str, default='127.0.0.1', help='server ip')
self.parser.add_argument(
'--port', type=int, default=8091, help='server port')
self.parser.add_argument(
'--input',
type=str,
default=None,
help='Audio file to be recognized',
required=True)
self.parser.add_argument(
'--sample_rate', type=int, default=16000, help='audio sample rate')
self.parser.add_argument(
'--lang', type=str, default="zh_cn", help='language')
self.parser.add_argument(
'--audio_format', type=str, default="wav", help='audio format')
def execute(self, argv: List[str]) -> bool:
args = self.parser.parse_args(argv)
input_ = args.input
server_ip = args.server_ip
port = args.port
sample_rate = args.sample_rate
lang = args.lang
audio_format = args.audio_format
try:
time_start = time.time()
res = self(
input=input_,
server_ip=server_ip,
port=port,
sample_rate=sample_rate,
lang=lang,
audio_format=audio_format)
time_end = time.time()
logger.info(res)
logger.info("Response time %f s." % (time_end - time_start))
return True
except Exception as e:
logger.error("Failed to speech recognition.")
logger.error(e)
return False
@stats_wrapper
def __call__(self,
input: str,
server_ip: str="127.0.0.1",
port: int=8091,
sample_rate: int=16000,
lang: str="zh_cn",
audio_format: str="wav"):
"""
Python API to call an executor.
"""
logger.info("asr websocket client start")
handler = ASRWsAudioHandler(server_ip, port)
loop = asyncio.get_event_loop()
res = loop.run_until_complete(handler.run(input))
logger.info("asr websocket client finished")
return res['result']
@cli_client_register(
name='paddlespeech_client.cls', description='visit cls service')
class CLSClientExecutor(BaseExecutor):
@ -521,4 +592,4 @@ class TextClientExecutor(BaseExecutor):
res = requests.post(url=url, data=json.dumps(request))
response_dict = res.json()
punc_text = response_dict["result"]["punc_text"]
return punc_text
return punc_text

Write Preview
Loading…
Cancel
Save