ImageRepositoryS3LangIdSignals

GoogleApi.ContentWarehouse.V1.Model.ImageRepositoryS3LangIdSignals

Table of Contents ▼

Jump to a specific part of the page:

Next Tag: 10

This module has the following attributes (case-insensitive ascending order):

View Attributes

containsSpeech (type: boolean(), default: nil)
- Whether this audio chunk has speech or not.
debuggingInfo (type: GoogleApi.ContentWarehouse.V1.Model.ImageRepositoryS3LangIdDebuggingInfo, default: nil)
-
endSec (type: String.t, default: nil)
-
langidResult (type: GoogleApi.ContentWarehouse.V1.Model.SpeechS3LanguageIdentificationResult, default: nil)
- S3 langID result. We keep langid_result even if contains_speech = false.
languageIdentification (type: GoogleApi.ContentWarehouse.V1.Model.VideoTimedtextS4ALIResults, default: nil)
- Converted version of the langid_result field, so that we have the YT compatible version of the langID result.
modelVersion (type: String.t, default: nil)
- The version of the model used for S3 LangID service.
speechFrameCount (type: integer(), default: nil)
-
startSec (type: String.t, default: nil)
- The audio chunk which corresponds to this langID result expressed as a start_sec and end_sec.
totalFrameCount (type: integer(), default: nil)
- Count the number of total frames in the audio chunk as well as the number of speech frames.

@type t() :: %GoogleApi.ContentWarehouse.V1.Model.ImageRepositoryS3LangIdSignals{
containsSpeech: boolean() | nil,
debuggingInfo: GoogleApi.ContentWarehouse.V1.Model.ImageRepositoryS3LangIdDebuggingInfo.t() | nil,
endSec: String.t() | nil,
langidResult: GoogleApi.ContentWarehouse.V1.Model.SpeechS3LanguageIdentificationResult.t() | nil,
languageIdentification: GoogleApi.ContentWarehouse.V1.Model.VideoTimedtextS4ALIResults.t() | nil,
modelVersion: String.t() | nil,
speechFrameCount: integer() | nil,
startSec: String.t() | nil,
totalFrameCount: integer() | nil
}

@spec decode(struct(), keyword()) :: struct()