BuildAllSpeakers
Trains Media Server to recognize any speakers that have not been trained.
You cannot train a speaker until you have added audio samples for training (using the action AddSpeakerAudio).
Type: asynchronous
| Parameter | Description | Required |
|---|---|---|
database
|
The name of a database to process. Set this parameter to train speakers in the specified database only. By default, this action trains speakers in all databases. | No |
gpudeviceid
|
The device ID of the GPU to use, if you have enabled GPU acceleration and want to override the value of the GPUDeviceID configuration parameter. You can also set this parameter to |
No |
numparallel
|
The maximum number of threads to use to complete the training (default 1), subject to the limit specified by MaxNumParallel. |
No |
Example
/action=BuildAllSpeakers&database=news
Response
This action is asynchronous, so Media Server always returns success accompanied by a token. You can use this token with the QueueInfo action to retrieve the status of your request.
The following is an example response from the QueueInfo action. Each entry element describes a speaker, and each audio element describes an individual audio clip.
<autnresponse>
<action>QUEUEINFO</action>
<response>SUCCESS</response>
<responsedata>
<actions>
<action>
<status>Finished</status>
<queued_time>2021-Feb-09 12:21:32</queued_time>
<time_in_queue>1</time_in_queue>
<process_start_time>2021-Feb-09 12:21:33</process_start_time>
<time_processing>139</time_processing>
<process_end_time>2021-Feb-09 12:23:52</process_end_time>
<entry>
<build>
<audio>
<index>1</index>
<label>bea4183e601660181ce6d4837ed211f2</label>
<status>trained</status>
</audio>
</build>
<database>news</database>
<identifier>newsreader1</identifier>
<numaudio>1</numaudio>
<numtrained>1</numtrained>
</entry>
...
<token>...</token>
</action>
</actions>
</responsedata>
</autnresponse>