Specifies how long to wait in transition mode before triggering a start of speech input event. Specifies an operating mode of VAD in the range of. Defaults to "NarrowbandModel" for 8kHz and "BroadbandModel" for 16kHz. If the timeout is elapsed, input is considered complete. Specifies a timeout between interim results containing transcribed speech. Specifies the URI of HTTP proxy, if used. Since WSR 1.4.0, if set to 0, the period is based on expires_in received in response from service. Specifies a period in seconds used to re-validate access token based on subscription key. The grammar can be referenced as builtin:speech/transcribe or builtin:grammar/transcribe, where transcribe is the default value of this parameter. Specifies the name of the built-in speech transcription grammar. Specifies whether to skip or raise an error while referencing a malformed or not supported grammar. Specifies the source of start of input event sent to the client (use "service-originated" to rely on service-originated first interim result and "internal" for plugin-originated event). Specifies an interval between 0.0 and 12.0 seconds at which the service splits a transcript into multiple final results if it encounters silence. Specifies whether the service returns signal characteristics of the input audio data. Specifies an interval in seconds at which the service returns processing metrics. Specifies whether the service returns metrics on transcription of the input audio data. Specifies whether the service returns masked numeric data having three or more consecutive digits. Specifies whether the service returns labels identifying a speaker for each word. Specifies whether the service returns time alignment for each word. Specifies whether the service returns a confidence for each word. Specifies whether the service converts dates, times, numbers, currency, and similar values into more conventional representations in the final transcript. Specifies the format of the confidence score to be returned (use "auto" for a format based on protocol version, "mrcpv2" for a float value in the range of 0.1, "mrcpv1" for an integer value in the range of 0.100). Specifies whether to return speech recognition result alternatives with the confidence score below the confidence threshold. Can be overridden by client by means of the header field N-Best-List-Length. Specifies the maximum number of speech recognition result alternatives to be returned. Specifies the weight to give to words from the custom language model compared to those from the base model, if any. Specifies the grammar name used for speech recognition in conjunction with the customization id of the custom language model for which the grammar is defined. Specifies the base model version to be used for recognition, if any. Specifies the custom acoustic model id to be used for recognition, if any. Specifies the custom language model id to be used for recognition, if any. For a list of supported languages, visit Specifies the default language to use, if not set by the client.
0 kommentar(er)
