Package io.spokestack.spokestack.profile

This package contains pre-built profiles used to configure the speech pipeline.

See: Description

Class Summary

Class	Description
PushToTalkAndroidASR	A speech pipeline profile that relies on manual pipeline activation, using Android's SpeechRecognizer API for ASR.
PushToTalkAzureASR	A speech pipeline profile that relies on manual pipeline activation, using Azure Speech Service for ASR.
PushToTalkGoogleASR	A speech pipeline profile that relies on manual pipeline activation, using Google Speech for ASR.
PushToTalkSpokestackASR	A speech pipeline profile that relies on manual pipeline activation, using Spokestack's cloud-based ASR.
TFWakewordAndroidASR	A speech pipeline profile that uses TensorFlow Lite for wakeword detection and Android's SpeechRecognizer API for ASR.
TFWakewordAzureASR	A speech pipeline profile that uses TensorFlow Lite for wakeword detection and Azure Speech Service for ASR.
TFWakewordGoogleASR	A speech pipeline profile that uses TensorFlow Lite for wakeword detection and Google Speech for ASR.
TFWakewordKeywordASR	A speech pipeline profile that uses TensorFlow Lite for wakeword detection and keyword detection-based ASR.
TFWakewordSpokestackASR	A speech pipeline profile that uses TensorFlow Lite for wakeword detection and Spokestack's cloud-based ASR.
VADTriggerAndroidASR	A speech pipeline profile that uses voice activity detection to activate Android's SpeechRecognizer API for ASR.
VADTriggerAzureASR	A speech pipeline profile that uses voice activity detection to activate ASR via Azure Speech Service.
VADTriggerGoogleASR	A speech pipeline profile that uses voice activity detection to activate Google Speech ASR.
VADTriggerKeywordASR	A speech pipeline profile that uses voice activity detection to activate ASR based on keyword detection.
VADTriggerSpokestackASR	A speech pipeline profile that uses voice activity detection to activate Spokestack's cloud-based ASR.

Package io.spokestack.spokestack.profile Description

This package contains pre-built profiles used to configure the speech pipeline.