Added azure_openai to agent-speech-processing.yaml. Fixed other providers
This commit is contained in:
pabloFuente
parent
32e533f892
commit
c692d9b86d
@ -58,6 +58,29 @@ live_captions:
|
||||
# See https://learn.microsoft.com/en-us/azure/ai-services/translator/profanity-filtering
|
||||
profanity:
|
||||
|
||||
azure_openai:
|
||||
# Credentials for Azure OpenAI APIs. See https://learn.microsoft.com/en-us/azure/api-management/api-management-authenticate-authorize-azure-openai
|
||||
# Azure OpenAI API key. Mandatory value.
|
||||
azure_api_key:
|
||||
# Azure Active Directory token. Mandatory value.
|
||||
azure_ad_token:
|
||||
# Azure OpenAI endpoint in the following format: https://{your-resource-name}.openai.azure.com. Mandatory value.
|
||||
azure_endpoint:
|
||||
# Name of your model deployment. If given with `azure_endpoint`, sets the base client URL to include `/deployments/{azure_deployment}`.
|
||||
azure_deployment:
|
||||
# OpenAI REST API version used for the request. Mandatory value.
|
||||
api_version:
|
||||
# OpenAI organization ID.
|
||||
organization:
|
||||
# OpenAI project ID.
|
||||
project:
|
||||
# The language code to use for transcription (e.g., "en" for English).
|
||||
language:
|
||||
# ID of the model to use for speech-to-text.
|
||||
model:
|
||||
# Initial prompt to guide the transcription.
|
||||
prompt:
|
||||
|
||||
google:
|
||||
# Credentials for Google Cloud. This is the content of a Google Cloud credential JSON file.
|
||||
# Below is a dummy example for a credential type of "Service Account" (https://cloud.google.com/iam/docs/service-account-creds#key-types)
|
||||
@ -155,13 +178,7 @@ live_captions:
|
||||
# API key for fal. See https://fal.ai/dashboard/keys
|
||||
api_key:
|
||||
# See https://fal.ai/models/fal-ai/wizper/api#schema
|
||||
task:
|
||||
# See https://fal.ai/models/fal-ai/wizper/api#schema
|
||||
language:
|
||||
# See https://fal.ai/models/fal-ai/wizper/api#schema
|
||||
chunk_level:
|
||||
# See https://fal.ai/models/fal-ai/wizper/api#schema
|
||||
version:
|
||||
|
||||
clova:
|
||||
# Secret key issued when registering the app
|
||||
@ -179,18 +196,28 @@ live_captions:
|
||||
speechmatics:
|
||||
# API key for Speechmatics. See https://portal.speechmatics.com/manage-access/
|
||||
api_key:
|
||||
# See https://docs.speechmatics.com/rt-api-ref#transcription-config
|
||||
# ISO 639-1 language code. All languages are global and can understand different dialects/accents. To see the list of all supported languages, see https://docs.speechmatics.com/introduction/supported-languages
|
||||
language:
|
||||
# See https://docs.speechmatics.com/features/accuracy-language-packs#output-locale
|
||||
output_locale:
|
||||
# See https://docs.speechmatics.com/features/realtime-latency#partial-transcripts
|
||||
# Operating point to use for the transcription per required accuracy & complexity. To learn more, see https://docs.speechmatics.com/features/accuracy-language-packs#accuracy
|
||||
operating_point:
|
||||
# Partial transcripts allow you to receive preliminary transcriptions and update as more context is available until the higher-accuracy final transcript is returned. Partials are returned faster but without any post-processing such as formatting. See https://docs.speechmatics.com/features/realtime-latency#partial-transcripts
|
||||
enable_partials:
|
||||
# See https://docs.speechmatics.com/features/realtime-latency#configuration-example
|
||||
# RFC-5646 language code to make spelling rules more consistent in the transcription output. See https://docs.speechmatics.com/features/word-tagging#output-locale
|
||||
output_locale:
|
||||
# The delay in seconds between the end of a spoken word and returning the final transcript results. See https://docs.speechmatics.com/features/realtime-latency#configuration-example
|
||||
max_delay:
|
||||
# See https://docs.speechmatics.com/features/realtime-latency#configuration-example
|
||||
max_delay_mode:
|
||||
# See https://docs.speechmatics.com/features/punctuation-settings
|
||||
# Commented below is an example of punctuation settings
|
||||
# Configuration for speaker diarization. See https://docs.speechmatics.com/features/diarization
|
||||
speaker_diarization_config:
|
||||
# See https://docs.speechmatics.com/features/diarization#max-speakers
|
||||
max_speakers:
|
||||
# See https://docs.speechmatics.com/features/diarization#speaker-sensitivity
|
||||
speaker_sensitivity:
|
||||
# See https://docs.speechmatics.com/features/diarization#prefer-current-speaker
|
||||
prefer_current_speaker:
|
||||
# Permitted puctuation marks for advanced punctuation. See https://docs.speechmatics.com/features/punctuation-settings
|
||||
# Commented is an example of punctuation settings
|
||||
punctuation_overrides:
|
||||
# permitted_marks: [ ".", "," ]
|
||||
# sensitivity: 0.4
|
||||
|
||||
@ -58,6 +58,29 @@ live_captions:
|
||||
# See https://learn.microsoft.com/en-us/azure/ai-services/translator/profanity-filtering
|
||||
profanity:
|
||||
|
||||
azure_openai:
|
||||
# Credentials for Azure OpenAI APIs. See https://learn.microsoft.com/en-us/azure/api-management/api-management-authenticate-authorize-azure-openai
|
||||
# Azure OpenAI API key. Mandatory value.
|
||||
azure_api_key:
|
||||
# Azure Active Directory token. Mandatory value.
|
||||
azure_ad_token:
|
||||
# Azure OpenAI endpoint in the following format: https://{your-resource-name}.openai.azure.com. Mandatory value.
|
||||
azure_endpoint:
|
||||
# Name of your model deployment. If given with `azure_endpoint`, sets the base client URL to include `/deployments/{azure_deployment}`.
|
||||
azure_deployment:
|
||||
# OpenAI REST API version used for the request. Mandatory value.
|
||||
api_version:
|
||||
# OpenAI organization ID.
|
||||
organization:
|
||||
# OpenAI project ID.
|
||||
project:
|
||||
# The language code to use for transcription (e.g., "en" for English).
|
||||
language:
|
||||
# ID of the model to use for speech-to-text.
|
||||
model:
|
||||
# Initial prompt to guide the transcription.
|
||||
prompt:
|
||||
|
||||
google:
|
||||
# Credentials for Google Cloud. This is the content of a Google Cloud credential JSON file.
|
||||
# Below is a dummy example for a credential type of "Service Account" (https://cloud.google.com/iam/docs/service-account-creds#key-types)
|
||||
@ -155,13 +178,7 @@ live_captions:
|
||||
# API key for fal. See https://fal.ai/dashboard/keys
|
||||
api_key:
|
||||
# See https://fal.ai/models/fal-ai/wizper/api#schema
|
||||
task:
|
||||
# See https://fal.ai/models/fal-ai/wizper/api#schema
|
||||
language:
|
||||
# See https://fal.ai/models/fal-ai/wizper/api#schema
|
||||
chunk_level:
|
||||
# See https://fal.ai/models/fal-ai/wizper/api#schema
|
||||
version:
|
||||
|
||||
clova:
|
||||
# Secret key issued when registering the app
|
||||
@ -179,18 +196,28 @@ live_captions:
|
||||
speechmatics:
|
||||
# API key for Speechmatics. See https://portal.speechmatics.com/manage-access/
|
||||
api_key:
|
||||
# See https://docs.speechmatics.com/rt-api-ref#transcription-config
|
||||
# ISO 639-1 language code. All languages are global and can understand different dialects/accents. To see the list of all supported languages, see https://docs.speechmatics.com/introduction/supported-languages
|
||||
language:
|
||||
# See https://docs.speechmatics.com/features/accuracy-language-packs#output-locale
|
||||
output_locale:
|
||||
# See https://docs.speechmatics.com/features/realtime-latency#partial-transcripts
|
||||
# Operating point to use for the transcription per required accuracy & complexity. To learn more, see https://docs.speechmatics.com/features/accuracy-language-packs#accuracy
|
||||
operating_point:
|
||||
# Partial transcripts allow you to receive preliminary transcriptions and update as more context is available until the higher-accuracy final transcript is returned. Partials are returned faster but without any post-processing such as formatting. See https://docs.speechmatics.com/features/realtime-latency#partial-transcripts
|
||||
enable_partials:
|
||||
# See https://docs.speechmatics.com/features/realtime-latency#configuration-example
|
||||
# RFC-5646 language code to make spelling rules more consistent in the transcription output. See https://docs.speechmatics.com/features/word-tagging#output-locale
|
||||
output_locale:
|
||||
# The delay in seconds between the end of a spoken word and returning the final transcript results. See https://docs.speechmatics.com/features/realtime-latency#configuration-example
|
||||
max_delay:
|
||||
# See https://docs.speechmatics.com/features/realtime-latency#configuration-example
|
||||
max_delay_mode:
|
||||
# See https://docs.speechmatics.com/features/punctuation-settings
|
||||
# Commented below is an example of punctuation settings
|
||||
# Configuration for speaker diarization. See https://docs.speechmatics.com/features/diarization
|
||||
speaker_diarization_config:
|
||||
# See https://docs.speechmatics.com/features/diarization#max-speakers
|
||||
max_speakers:
|
||||
# See https://docs.speechmatics.com/features/diarization#speaker-sensitivity
|
||||
speaker_sensitivity:
|
||||
# See https://docs.speechmatics.com/features/diarization#prefer-current-speaker
|
||||
prefer_current_speaker:
|
||||
# Permitted puctuation marks for advanced punctuation. See https://docs.speechmatics.com/features/punctuation-settings
|
||||
# Commented is an example of punctuation settings
|
||||
punctuation_overrides:
|
||||
# permitted_marks: [ ".", "," ]
|
||||
# sensitivity: 0.4
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user