Reference documentation and code samples for the Cloud Speech-to-Text V1 API class Google::Cloud::Speech::V1::RecognitionConfig.
Provides information to the recognizer that specifies how to process the request.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#adaptation
def adaptation() -> ::Google::Cloud::Speech::V1::SpeechAdaptation
-
(::Google::Cloud::Speech::V1::SpeechAdaptation) — Speech adaptation configuration improves the accuracy of speech
recognition. For more information, see the speech
adaptation
documentation.
When speech adaptation is set it supersedes the
speech_contexts
field.
#adaptation=
def adaptation=(value) -> ::Google::Cloud::Speech::V1::SpeechAdaptation
-
value (::Google::Cloud::Speech::V1::SpeechAdaptation) — Speech adaptation configuration improves the accuracy of speech
recognition. For more information, see the speech
adaptation
documentation.
When speech adaptation is set it supersedes the
speech_contexts
field.
-
(::Google::Cloud::Speech::V1::SpeechAdaptation) — Speech adaptation configuration improves the accuracy of speech
recognition. For more information, see the speech
adaptation
documentation.
When speech adaptation is set it supersedes the
speech_contexts
field.
#alternative_language_codes
def alternative_language_codes() -> ::Array<::String>
- (::Array<::String>) — A list of up to 3 additional BCP-47 language tags, listing possible alternative languages of the supplied audio. See Language Support for a list of the currently supported language codes. If alternative languages are listed, recognition result will contain recognition in the most likely language detected including the main language_code. The recognition result will include the language tag of the language detected in the audio. Note: This feature is only supported for Voice Command and Voice Search use cases and performance may vary for other use cases (e.g., phone call transcription).
#alternative_language_codes=
def alternative_language_codes=(value) -> ::Array<::String>
- value (::Array<::String>) — A list of up to 3 additional BCP-47 language tags, listing possible alternative languages of the supplied audio. See Language Support for a list of the currently supported language codes. If alternative languages are listed, recognition result will contain recognition in the most likely language detected including the main language_code. The recognition result will include the language tag of the language detected in the audio. Note: This feature is only supported for Voice Command and Voice Search use cases and performance may vary for other use cases (e.g., phone call transcription).
- (::Array<::String>) — A list of up to 3 additional BCP-47 language tags, listing possible alternative languages of the supplied audio. See Language Support for a list of the currently supported language codes. If alternative languages are listed, recognition result will contain recognition in the most likely language detected including the main language_code. The recognition result will include the language tag of the language detected in the audio. Note: This feature is only supported for Voice Command and Voice Search use cases and performance may vary for other use cases (e.g., phone call transcription).
#audio_channel_count
def audio_channel_count() -> ::Integer
-
(::Integer) — The number of channels in the input audio data.
ONLY set this for MULTI-CHANNEL recognition.
Valid values for LINEAR16, OGG_OPUS and FLAC are
1
-8
. Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only1
. If0
or omitted, defaults to one channel (mono). Note: We only recognize the first channel by default. To perform independent recognition on each channel setenable_separate_recognition_per_channel
to 'true'.
#audio_channel_count=
def audio_channel_count=(value) -> ::Integer
-
value (::Integer) — The number of channels in the input audio data.
ONLY set this for MULTI-CHANNEL recognition.
Valid values for LINEAR16, OGG_OPUS and FLAC are
1
-8
. Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only1
. If0
or omitted, defaults to one channel (mono). Note: We only recognize the first channel by default. To perform independent recognition on each channel setenable_separate_recognition_per_channel
to 'true'.
-
(::Integer) — The number of channels in the input audio data.
ONLY set this for MULTI-CHANNEL recognition.
Valid values for LINEAR16, OGG_OPUS and FLAC are
1
-8
. Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only1
. If0
or omitted, defaults to one channel (mono). Note: We only recognize the first channel by default. To perform independent recognition on each channel setenable_separate_recognition_per_channel
to 'true'.
#diarization_config
def diarization_config() -> ::Google::Cloud::Speech::V1::SpeakerDiarizationConfig
- (::Google::Cloud::Speech::V1::SpeakerDiarizationConfig) — Config to enable speaker diarization and set additional parameters to make diarization better suited for your application. Note: When this is enabled, we send all the words from the beginning of the audio for the top alternative in every consecutive STREAMING responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time. For non-streaming requests, the diarization results will be provided only in the top alternative of the FINAL SpeechRecognitionResult.
#diarization_config=
def diarization_config=(value) -> ::Google::Cloud::Speech::V1::SpeakerDiarizationConfig
- value (::Google::Cloud::Speech::V1::SpeakerDiarizationConfig) — Config to enable speaker diarization and set additional parameters to make diarization better suited for your application. Note: When this is enabled, we send all the words from the beginning of the audio for the top alternative in every consecutive STREAMING responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time. For non-streaming requests, the diarization results will be provided only in the top alternative of the FINAL SpeechRecognitionResult.
- (::Google::Cloud::Speech::V1::SpeakerDiarizationConfig) — Config to enable speaker diarization and set additional parameters to make diarization better suited for your application. Note: When this is enabled, we send all the words from the beginning of the audio for the top alternative in every consecutive STREAMING responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time. For non-streaming requests, the diarization results will be provided only in the top alternative of the FINAL SpeechRecognitionResult.
#enable_automatic_punctuation
def enable_automatic_punctuation() -> ::Boolean
- (::Boolean) — If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses.
#enable_automatic_punctuation=
def enable_automatic_punctuation=(value) -> ::Boolean
- value (::Boolean) — If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses.
- (::Boolean) — If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses.
#enable_separate_recognition_per_channel
def enable_separate_recognition_per_channel() -> ::Boolean
-
(::Boolean) — This needs to be set to
true
explicitly andaudio_channel_count
> 1 to get each channel recognized separately. The recognition result will contain achannel_tag
field to state which channel that result belongs to. If this is not true, we will only recognize the first channel. The request is billed cumulatively for all channels recognized:audio_channel_count
multiplied by the length of the audio.
#enable_separate_recognition_per_channel=
def enable_separate_recognition_per_channel=(value) -> ::Boolean
-
value (::Boolean) — This needs to be set to
true
explicitly andaudio_channel_count
> 1 to get each channel recognized separately. The recognition result will contain achannel_tag
field to state which channel that result belongs to. If this is not true, we will only recognize the first channel. The request is billed cumulatively for all channels recognized:audio_channel_count
multiplied by the length of the audio.
-
(::Boolean) — This needs to be set to
true
explicitly andaudio_channel_count
> 1 to get each channel recognized separately. The recognition result will contain achannel_tag
field to state which channel that result belongs to. If this is not true, we will only recognize the first channel. The request is billed cumulatively for all channels recognized:audio_channel_count
multiplied by the length of the audio.
#enable_spoken_emojis
def enable_spoken_emojis() -> ::Google::Protobuf::BoolValue
- (::Google::Protobuf::BoolValue) — The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If 'true', adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If 'false', spoken emojis are not replaced.
#enable_spoken_emojis=
def enable_spoken_emojis=(value) -> ::Google::Protobuf::BoolValue
- value (::Google::Protobuf::BoolValue) — The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If 'true', adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If 'false', spoken emojis are not replaced.
- (::Google::Protobuf::BoolValue) — The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If 'true', adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If 'false', spoken emojis are not replaced.
#enable_spoken_punctuation
def enable_spoken_punctuation() -> ::Google::Protobuf::BoolValue
- (::Google::Protobuf::BoolValue) — The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If 'true', replaces spoken punctuation with the corresponding symbols in the request. For example, "how are you question mark" becomes "how are you?". See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If 'false', spoken punctuation is not replaced.
#enable_spoken_punctuation=
def enable_spoken_punctuation=(value) -> ::Google::Protobuf::BoolValue
- value (::Google::Protobuf::BoolValue) — The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If 'true', replaces spoken punctuation with the corresponding symbols in the request. For example, "how are you question mark" becomes "how are you?". See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If 'false', spoken punctuation is not replaced.
- (::Google::Protobuf::BoolValue) — The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If 'true', replaces spoken punctuation with the corresponding symbols in the request. For example, "how are you question mark" becomes "how are you?". See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If 'false', spoken punctuation is not replaced.
#enable_word_confidence
def enable_word_confidence() -> ::Boolean
-
(::Boolean) — If
true
, the top result includes a list of words and the confidence for those words. Iffalse
, no word-level confidence information is returned. The default isfalse
.
#enable_word_confidence=
def enable_word_confidence=(value) -> ::Boolean
-
value (::Boolean) — If
true
, the top result includes a list of words and the confidence for those words. Iffalse
, no word-level confidence information is returned. The default isfalse
.
-
(::Boolean) — If
true
, the top result includes a list of words and the confidence for those words. Iffalse
, no word-level confidence information is returned. The default isfalse
.
#enable_word_time_offsets
def enable_word_time_offsets() -> ::Boolean
-
(::Boolean) — If
true
, the top result includes a list of words and the start and end time offsets (timestamps) for those words. Iffalse
, no word-level time offset information is returned. The default isfalse
.
#enable_word_time_offsets=
def enable_word_time_offsets=(value) -> ::Boolean
-
value (::Boolean) — If
true
, the top result includes a list of words and the start and end time offsets (timestamps) for those words. Iffalse
, no word-level time offset information is returned. The default isfalse
.
-
(::Boolean) — If
true
, the top result includes a list of words and the start and end time offsets (timestamps) for those words. Iffalse
, no word-level time offset information is returned. The default isfalse
.
#encoding
def encoding() -> ::Google::Cloud::Speech::V1::RecognitionConfig::AudioEncoding
-
(::Google::Cloud::Speech::V1::RecognitionConfig::AudioEncoding) — Encoding of audio data sent in all
RecognitionAudio
messages. This field is optional forFLAC
andWAV
audio files and required for all other audio formats. For details, see AudioEncoding.
#encoding=
def encoding=(value) -> ::Google::Cloud::Speech::V1::RecognitionConfig::AudioEncoding
-
value (::Google::Cloud::Speech::V1::RecognitionConfig::AudioEncoding) — Encoding of audio data sent in all
RecognitionAudio
messages. This field is optional forFLAC
andWAV
audio files and required for all other audio formats. For details, see AudioEncoding.
-
(::Google::Cloud::Speech::V1::RecognitionConfig::AudioEncoding) — Encoding of audio data sent in all
RecognitionAudio
messages. This field is optional forFLAC
andWAV
audio files and required for all other audio formats. For details, see AudioEncoding.
#language_code
def language_code() -> ::String
- (::String) — Required. The language of the supplied audio as a BCP-47 language tag. Example: "en-US". See Language Support for a list of the currently supported language codes.
#language_code=
def language_code=(value) -> ::String
- value (::String) — Required. The language of the supplied audio as a BCP-47 language tag. Example: "en-US". See Language Support for a list of the currently supported language codes.
- (::String) — Required. The language of the supplied audio as a BCP-47 language tag. Example: "en-US". See Language Support for a list of the currently supported language codes.
#max_alternatives
def max_alternatives() -> ::Integer
-
(::Integer) — Maximum number of recognition hypotheses to be returned.
Specifically, the maximum number of
SpeechRecognitionAlternative
messages within eachSpeechRecognitionResult
. The server may return fewer thanmax_alternatives
. Valid values are0
-30
. A value of0
or1
will return a maximum of one. If omitted, will return a maximum of one.
#max_alternatives=
def max_alternatives=(value) -> ::Integer
-
value (::Integer) — Maximum number of recognition hypotheses to be returned.
Specifically, the maximum number of
SpeechRecognitionAlternative
messages within eachSpeechRecognitionResult
. The server may return fewer thanmax_alternatives
. Valid values are0
-30
. A value of0
or1
will return a maximum of one. If omitted, will return a maximum of one.
-
(::Integer) — Maximum number of recognition hypotheses to be returned.
Specifically, the maximum number of
SpeechRecognitionAlternative
messages within eachSpeechRecognitionResult
. The server may return fewer thanmax_alternatives
. Valid values are0
-30
. A value of0
or1
will return a maximum of one. If omitted, will return a maximum of one.
#metadata
def metadata() -> ::Google::Cloud::Speech::V1::RecognitionMetadata
- (::Google::Cloud::Speech::V1::RecognitionMetadata) — Metadata regarding this request.
#metadata=
def metadata=(value) -> ::Google::Cloud::Speech::V1::RecognitionMetadata
- value (::Google::Cloud::Speech::V1::RecognitionMetadata) — Metadata regarding this request.
- (::Google::Cloud::Speech::V1::RecognitionMetadata) — Metadata regarding this request.
#model
def model() -> ::String
-
(::String) —
Which model to select for the given request. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then we auto-select a model based on the parameters in the RecognitionConfig.
Model Description latest_long
Best for long form content like media or conversation. latest_short
Best for short form content like commands or single shot directed speech. command_and_search
Best for short queries such as voice commands or voice search. phone_call
Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate). video
Best for audio that originated from video or includes multiple speakers. Ideally the audio is recorded at a 16khz or greater sampling rate. This is a premium model that costs more than the standard rate. default
Best for audio that is not one of the specific audio models. For example, long-form audio. Ideally the audio is high-fidelity, recorded at a 16khz or greater sampling rate. medical_conversation
Best for audio that originated from a conversation between a medical provider and patient. medical_dictation
Best for audio that originated from dictation notes by a medical provider.
#model=
def model=(value) -> ::String
-
value (::String) —
Which model to select for the given request. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then we auto-select a model based on the parameters in the RecognitionConfig.
Model Description latest_long
Best for long form content like media or conversation. latest_short
Best for short form content like commands or single shot directed speech. command_and_search
Best for short queries such as voice commands or voice search. phone_call
Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate). video
Best for audio that originated from video or includes multiple speakers. Ideally the audio is recorded at a 16khz or greater sampling rate. This is a premium model that costs more than the standard rate. default
Best for audio that is not one of the specific audio models. For example, long-form audio. Ideally the audio is high-fidelity, recorded at a 16khz or greater sampling rate. medical_conversation
Best for audio that originated from a conversation between a medical provider and patient. medical_dictation
Best for audio that originated from dictation notes by a medical provider.
-
(::String) —
Which model to select for the given request. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then we auto-select a model based on the parameters in the RecognitionConfig.
Model Description latest_long
Best for long form content like media or conversation. latest_short
Best for short form content like commands or single shot directed speech. command_and_search
Best for short queries such as voice commands or voice search. phone_call
Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate). video
Best for audio that originated from video or includes multiple speakers. Ideally the audio is recorded at a 16khz or greater sampling rate. This is a premium model that costs more than the standard rate. default
Best for audio that is not one of the specific audio models. For example, long-form audio. Ideally the audio is high-fidelity, recorded at a 16khz or greater sampling rate. medical_conversation
Best for audio that originated from a conversation between a medical provider and patient. medical_dictation
Best for audio that originated from dictation notes by a medical provider.
#profanity_filter
def profanity_filter() -> ::Boolean
-
(::Boolean) — If set to
true
, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. "f***". If set tofalse
or omitted, profanities won't be filtered out.
#profanity_filter=
def profanity_filter=(value) -> ::Boolean
-
value (::Boolean) — If set to
true
, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. "f***". If set tofalse
or omitted, profanities won't be filtered out.
-
(::Boolean) — If set to
true
, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. "f***". If set tofalse
or omitted, profanities won't be filtered out.
#sample_rate_hertz
def sample_rate_hertz() -> ::Integer
-
(::Integer) — Sample rate in Hertz of the audio data sent in all
RecognitionAudio
messages. Valid values are: 8000-48000. 16000 is optimal. For best results, set the sampling rate of the audio source to 16000 Hz. If that's not possible, use the native sample rate of the audio source (instead of re-sampling). This field is optional for FLAC and WAV audio files, but is required for all other audio formats. For details, see AudioEncoding.
#sample_rate_hertz=
def sample_rate_hertz=(value) -> ::Integer
-
value (::Integer) — Sample rate in Hertz of the audio data sent in all
RecognitionAudio
messages. Valid values are: 8000-48000. 16000 is optimal. For best results, set the sampling rate of the audio source to 16000 Hz. If that's not possible, use the native sample rate of the audio source (instead of re-sampling). This field is optional for FLAC and WAV audio files, but is required for all other audio formats. For details, see AudioEncoding.
-
(::Integer) — Sample rate in Hertz of the audio data sent in all
RecognitionAudio
messages. Valid values are: 8000-48000. 16000 is optimal. For best results, set the sampling rate of the audio source to 16000 Hz. If that's not possible, use the native sample rate of the audio source (instead of re-sampling). This field is optional for FLAC and WAV audio files, but is required for all other audio formats. For details, see AudioEncoding.
#speech_contexts
def speech_contexts() -> ::Array<::Google::Cloud::Speech::V1::SpeechContext>
- (::Array<::Google::Cloud::Speech::V1::SpeechContext>) — Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see speech adaptation.
#speech_contexts=
def speech_contexts=(value) -> ::Array<::Google::Cloud::Speech::V1::SpeechContext>
- value (::Array<::Google::Cloud::Speech::V1::SpeechContext>) — Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see speech adaptation.
- (::Array<::Google::Cloud::Speech::V1::SpeechContext>) — Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see speech adaptation.
#transcript_normalization
def transcript_normalization() -> ::Google::Cloud::Speech::V1::TranscriptNormalization
- (::Google::Cloud::Speech::V1::TranscriptNormalization) — Optional. Use transcription normalization to automatically replace parts of the transcript with phrases of your choosing. For StreamingRecognize, this normalization only applies to stable partial transcripts (stability > 0.8) and final transcripts.
#transcript_normalization=
def transcript_normalization=(value) -> ::Google::Cloud::Speech::V1::TranscriptNormalization
- value (::Google::Cloud::Speech::V1::TranscriptNormalization) — Optional. Use transcription normalization to automatically replace parts of the transcript with phrases of your choosing. For StreamingRecognize, this normalization only applies to stable partial transcripts (stability > 0.8) and final transcripts.
- (::Google::Cloud::Speech::V1::TranscriptNormalization) — Optional. Use transcription normalization to automatically replace parts of the transcript with phrases of your choosing. For StreamingRecognize, this normalization only applies to stable partial transcripts (stability > 0.8) and final transcripts.
#use_enhanced
def use_enhanced() -> ::Boolean
-
(::Boolean) — Set to true to use an enhanced model for speech recognition.
If
use_enhanced
is set to true and themodel
field is not set, then an appropriate enhanced model is chosen if an enhanced model exists for the audio.If
use_enhanced
is true and an enhanced version of the specified model does not exist, then the speech is recognized using the standard version of the specified model.
#use_enhanced=
def use_enhanced=(value) -> ::Boolean
-
value (::Boolean) — Set to true to use an enhanced model for speech recognition.
If
use_enhanced
is set to true and themodel
field is not set, then an appropriate enhanced model is chosen if an enhanced model exists for the audio.If
use_enhanced
is true and an enhanced version of the specified model does not exist, then the speech is recognized using the standard version of the specified model.
-
(::Boolean) — Set to true to use an enhanced model for speech recognition.
If
use_enhanced
is set to true and themodel
field is not set, then an appropriate enhanced model is chosen if an enhanced model exists for the audio.If
use_enhanced
is true and an enhanced version of the specified model does not exist, then the speech is recognized using the standard version of the specified model.