SR Websocket
- 19 Jul 2024
- 2 Minutes to read
- Contributors
- Print
- PDF
SR Websocket
- Updated on 19 Jul 2024
- 2 Minutes to read
- Contributors
- Print
- PDF
Article summary
Did you find this summary helpful?
Thank you for your feedback
Performs speech recognition. Uses SestekSR with web socket protocol.
Parameters:
name | description | default |
|---|---|---|
| Address | Address of SestekSR that will be used for performing recognitions | http://core-sr |
| IgnoreSslErrors | ignore any certificate errors if SestekSR address contains https | false |
| ConnectionTimeoutMsec | SestekSR Connection timeout in terms of milliseconds | 5000 |
| CredentialId | Id of the credential that will be used for SestekSR recognitions. This parameter is only necessary if a cloud SestekSR deployment is used. You shall leave this empty for on-premise deployments, it will be ignored anyway | None(On-Prem) |
| Language | Language will be used in order to determine which of the provided models will be used for recognition. | |
| Models | A list of models with different languages that can be used in the recognitions. |
Inputs
Audio:
Accepts audio from a single channel. Passing the audio through a VAD node before streaming to this node is recommended.
Events:
name | description | known nodes that generate this event |
|---|---|---|
| Language Change | Changes the language parameter. The recognitions requested after this event will use the updated language (hence appropriate model) | Language Identifier, Text Language Identifier |
Outputs
Audio:
none
Events:
default | description |
|---|---|
| SR Milestone | Raised for each piece of speech in the provided audio data. This event contains recognition results for a single piece of speech. "sr-milestone" results are cumulative. The total recognition result in the end can be prepared by concatenating all the sr-milestone events' texts |
| SR Partial | Shall be raised several times for the current piece of speech that is being recognized at the moment. An "sr-partial" event replaces any previous "sr-partial" event that has been raised for the same piece of speech. "sr-partial" event resets after a "sr-milestone" event has been raised. The total recognition text at a specific point in time can be prepared by concatenating all the previous "sr-milestone" events' texts and adding the latest "sr-partial" event's text at the end. |
License : Needs "sr-websocket" option
Remarks :
*Not all models can generate partial recognition results. At the moment this document is being prepared end-to-end models still lack this ability.
Service Link Parametrization:
The default address for this node is http://core-sr . This default link is intended for on-premise installations.
When SestekSr is deployed in the cloud SestekSR uses a http address that depends on the name of the model it hosts. eg.
http://core-sr-turkish
http://core-sr-english
http://core-sr-arabic
In order to use a single link in the cloud that you won't need to change every time you switch your models you should prefer the link with the {model_title} placeholder. ie. your default link should be the following: http://core-sr-{model_title}
Project Structure
A simple project utilizing SR WebSocket can be built as such:
Events
Note that SR WebSocket only processes Language Change events. So no other event input from any node other than Language Identifier or Text Language Identifier is needed.
Another simple project that can react to language changes can be built as such:
Compatibility
SR Websocket outputs SR Milestone and SR Partial events. Which means every node that is compatible with SR Http is also compatible with SR Websocket. You can check the SR Http page to learn more about compatible nodes.
Supported flow types: Stream
Was this article helpful?