1. Add the API of the KWS plug-in to the **//foundation/ai/engine/services/server/plugin** directory. This API is used to call AI capabilities. The following code snippet is an example API implementation of the KWS plug-in. The reference code is available at the **//foundation/ai/engine/services/server/plugin/asr/keyword\_spotting** directory.
1. Add the API of the KWS plug-in to the **//foundation/ai/engine/services/server/plugin** directory. This API is used to call AI capabilities. The following code snippet is an example API implementation of the KWS plug-in. The reference code is available at the **//foundation/ai/engine/services/server/plugin/asr/keyword\_spotting** directory.
```
#include "plugin/i_plugin.h
...
...
@@ -20,72 +20,23 @@
};
```
The preceding code implements the **IPlugin** API provided by the server. [Table 1](#table567211582104) shows the mapping between the client APIs and the plug-in APIs.
The preceding code implements the **IPlugin** API provided by the server. [Table 1](#table567211582104) shows the mapping between the client APIs and the plug-in APIs.
**Table 1** Mapping between the client APIs and the plug-in APIs
**Table 1** Mapping between the client APIs and the plug-in APIs
<td class="cellrowborder" valign="top" width="59.25592559255926%" headers="mcps1.2.4.1.3 "><p id="p5672105816102"><a name="p5672105816102"></a><a name="p5672105816102"></a>Initializes the inference algorithm plug-in. For KWS, this API loads the KWS model from the fixed location (<strong id="b138031131115020"><a name="b138031131115020"></a><a name="b138031131115020"></a>/sdcard/wenwen_inst.wk</strong>) to the memory.</p>
<td class="cellrowborder" valign="top" width="59.25592559255926%" headers="mcps1.2.4.1.3 "><p id="p767275811010"><a name="p767275811010"></a><a name="p767275811010"></a>Executes the inference algorithm synchronously. For KWS, this API synchronously executes the audio inference algorithm to determine whether the specified wakeup keyword exists in the audio.</p>
<td class="cellrowborder" valign="top" width="59.25592559255926%" headers="mcps1.2.4.1.3 "><p id="p56731758151018"><a name="p56731758151018"></a><a name="p56731758151018"></a>Executes the inference algorithm asynchronously. Currently, this API is not used in KWS. However, you can implement the API based on your use case.</p>
<td class="cellrowborder" valign="top" width="59.25592559255926%" headers="mcps1.2.4.1.3 "><p id="p76731158121018"><a name="p76731158121018"></a><a name="p76731158121018"></a>Sets algorithm-related configuration items, such as the confidence threshold and delay. Currently, this API is not used in KWS. However, you can implement the API based on your use case.</p>
<td class="cellrowborder" valign="top" width="59.25592559255926%" headers="mcps1.2.4.1.3 "><p id="p106732581109"><a name="p106732581109"></a><a name="p106732581109"></a>Obtains algorithm-related configuration items. For KWS, this API can obtain the input and output scale of the KWS model. The input scale is the MFCC feature (fixed value: 4000) required by the KWS model, and the output scale is the confidence (fixed value: 2) of the result.</p>
<td class="cellrowborder" valign="top" width="59.25592559255926%" headers="mcps1.2.4.1.3 "><p id="p467318586105"><a name="p467318586105"></a><a name="p467318586105"></a>Releases the algorithm model. For KWS, this API releases the specified algorithm model and clears the dynamic memory in the feature processor.</p>
</td>
</tr>
</tbody>
</table>
Note:
1. The **AieClientInit** and **AieClientDestroy** APIs are used to connect to and disconnect from the server, respectively. They are not called in the plug-in algorithm and therefore do not need to be defined in the plug-in.
2. The KWS plug-in needs to use the **PLUGIN\_INTERFACE\_IMPL** statement to expose the function pointer. Otherwise, the plug-in cannot be properly loaded.
| Client API | Plug-in API | Description |
| ---------- | ----------- | ----------- |
| AieClientPrepare | Prepare | Initializes the inference algorithm plug-in. For KWS, this API loads the KWS model from the fixed location (/sdcard/wenwen_inst.wk) to the memory. |
| AieClientSyncProcess | SyncProcess | Executes the inference algorithm synchronously. For KWS, this API synchronously executes the audio inference algorithm to determine whether the specified wakeup keyword exists in the audio. |
| AieClientAsyncProcess | AsyncProcess | Executes the inference algorithm asynchronously. Currently, this API is not used in KWS. However, you can implement the API based on your use case. |
| AieClientSetOption | SetOption | Sets algorithm-related configuration items, such as the confidence threshold and delay. Currently, this API is not used in KWS. However, you can implement the API based on your use case. |
| AieClientGetOption | GetOption | Obtains algorithm-related configuration items. For KWS, this API can obtain the input and output scale of the KWS model. The input scale is the MFCC feature (fixed value: 4000) required by the KWS model, and the output scale is the confidence (fixed value: 2) of the result. |
| AieClientRelease | Release | Releases the algorithm model. For KWS, this API releases the specified algorithm model and clears the dynamic memory in the feature processor. |
>- The **AieClientInit** and **AieClientDestroy** APIs are used to connect to and disconnect from the server, respectively. They are not called in the plug-in algorithm and therefore do not need to be defined in the plug-in.
>- The KWS plug-in needs to use the **PLUGIN\_INTERFACE\_IMPL** statement to expose the function pointer. Otherwise, the plug-in cannot be properly loaded.
