Variables
RecognitionConfig_AudioEncoding_name, RecognitionConfig_AudioEncoding_value
var (
RecognitionConfig_AudioEncoding_name = map[int32]string{
0: "ENCODING_UNSPECIFIED",
1: "LINEAR16",
2: "FLAC",
3: "MULAW",
4: "AMR",
5: "AMR_WB",
6: "OGG_OPUS",
7: "SPEEX_WITH_HEADER_BYTE",
9: "WEBM_OPUS",
}
RecognitionConfig_AudioEncoding_value = map[string]int32{
"ENCODING_UNSPECIFIED": 0,
"LINEAR16": 1,
"FLAC": 2,
"MULAW": 3,
"AMR": 4,
"AMR_WB": 5,
"OGG_OPUS": 6,
"SPEEX_WITH_HEADER_BYTE": 7,
"WEBM_OPUS": 9,
}
)
Enum value maps for RecognitionConfig_AudioEncoding.
RecognitionMetadata_InteractionType_name, RecognitionMetadata_InteractionType_value
var (
RecognitionMetadata_InteractionType_name = map[int32]string{
0: "INTERACTION_TYPE_UNSPECIFIED",
1: "DISCUSSION",
2: "PRESENTATION",
3: "PHONE_CALL",
4: "VOICEMAIL",
5: "PROFESSIONALLY_PRODUCED",
6: "VOICE_SEARCH",
7: "VOICE_COMMAND",
8: "DICTATION",
}
RecognitionMetadata_InteractionType_value = map[string]int32{
"INTERACTION_TYPE_UNSPECIFIED": 0,
"DISCUSSION": 1,
"PRESENTATION": 2,
"PHONE_CALL": 3,
"VOICEMAIL": 4,
"PROFESSIONALLY_PRODUCED": 5,
"VOICE_SEARCH": 6,
"VOICE_COMMAND": 7,
"DICTATION": 8,
}
)
Enum value maps for RecognitionMetadata_InteractionType.
RecognitionMetadata_MicrophoneDistance_name, RecognitionMetadata_MicrophoneDistance_value
var (
RecognitionMetadata_MicrophoneDistance_name = map[int32]string{
0: "MICROPHONE_DISTANCE_UNSPECIFIED",
1: "NEARFIELD",
2: "MIDFIELD",
3: "FARFIELD",
}
RecognitionMetadata_MicrophoneDistance_value = map[string]int32{
"MICROPHONE_DISTANCE_UNSPECIFIED": 0,
"NEARFIELD": 1,
"MIDFIELD": 2,
"FARFIELD": 3,
}
)
Enum value maps for RecognitionMetadata_MicrophoneDistance.
RecognitionMetadata_OriginalMediaType_name, RecognitionMetadata_OriginalMediaType_value
var (
RecognitionMetadata_OriginalMediaType_name = map[int32]string{
0: "ORIGINAL_MEDIA_TYPE_UNSPECIFIED",
1: "AUDIO",
2: "VIDEO",
}
RecognitionMetadata_OriginalMediaType_value = map[string]int32{
"ORIGINAL_MEDIA_TYPE_UNSPECIFIED": 0,
"AUDIO": 1,
"VIDEO": 2,
}
)
Enum value maps for RecognitionMetadata_OriginalMediaType.
RecognitionMetadata_RecordingDeviceType_name, RecognitionMetadata_RecordingDeviceType_value
var (
RecognitionMetadata_RecordingDeviceType_name = map[int32]string{
0: "RECORDING_DEVICE_TYPE_UNSPECIFIED",
1: "SMARTPHONE",
2: "PC",
3: "PHONE_LINE",
4: "VEHICLE",
5: "OTHER_OUTDOOR_DEVICE",
6: "OTHER_INDOOR_DEVICE",
}
RecognitionMetadata_RecordingDeviceType_value = map[string]int32{
"RECORDING_DEVICE_TYPE_UNSPECIFIED": 0,
"SMARTPHONE": 1,
"PC": 2,
"PHONE_LINE": 3,
"VEHICLE": 4,
"OTHER_OUTDOOR_DEVICE": 5,
"OTHER_INDOOR_DEVICE": 6,
}
)
Enum value maps for RecognitionMetadata_RecordingDeviceType.
StreamingRecognizeResponse_SpeechEventType_name, StreamingRecognizeResponse_SpeechEventType_value
var (
StreamingRecognizeResponse_SpeechEventType_name = map[int32]string{
0: "SPEECH_EVENT_UNSPECIFIED",
1: "END_OF_SINGLE_UTTERANCE",
2: "SPEECH_ACTIVITY_BEGIN",
3: "SPEECH_ACTIVITY_END",
4: "SPEECH_ACTIVITY_TIMEOUT",
}
StreamingRecognizeResponse_SpeechEventType_value = map[string]int32{
"SPEECH_EVENT_UNSPECIFIED": 0,
"END_OF_SINGLE_UTTERANCE": 1,
"SPEECH_ACTIVITY_BEGIN": 2,
"SPEECH_ACTIVITY_END": 3,
"SPEECH_ACTIVITY_TIMEOUT": 4,
}
)
Enum value maps for StreamingRecognizeResponse_SpeechEventType.
File_google_cloud_speech_v1_cloud_speech_adaptation_proto
var File_google_cloud_speech_v1_cloud_speech_adaptation_proto protoreflect.FileDescriptor
File_google_cloud_speech_v1_cloud_speech_proto
var File_google_cloud_speech_v1_cloud_speech_proto protoreflect.FileDescriptor
File_google_cloud_speech_v1_resource_proto
var File_google_cloud_speech_v1_resource_proto protoreflect.FileDescriptor
Functions
func RegisterAdaptationServer
func RegisterAdaptationServer(s *grpc.Server, srv AdaptationServer)
func RegisterSpeechServer
func RegisterSpeechServer(s *grpc.Server, srv SpeechServer)
AdaptationClient
type AdaptationClient interface {
// Create a set of phrase hints. Each item in the set can be a single word or
// a multi-word phrase. The items in the PhraseSet are favored by the
// recognition model when you send a call that includes the PhraseSet.
CreatePhraseSet(ctx context.Context, in *CreatePhraseSetRequest, opts ...grpc.CallOption) (*PhraseSet, error)
// Get a phrase set.
GetPhraseSet(ctx context.Context, in *GetPhraseSetRequest, opts ...grpc.CallOption) (*PhraseSet, error)
// List phrase sets.
ListPhraseSet(ctx context.Context, in *ListPhraseSetRequest, opts ...grpc.CallOption) (*ListPhraseSetResponse, error)
// Update a phrase set.
UpdatePhraseSet(ctx context.Context, in *UpdatePhraseSetRequest, opts ...grpc.CallOption) (*PhraseSet, error)
// Delete a phrase set.
DeletePhraseSet(ctx context.Context, in *DeletePhraseSetRequest, opts ...grpc.CallOption) (*emptypb.Empty, error)
// Create a custom class.
CreateCustomClass(ctx context.Context, in *CreateCustomClassRequest, opts ...grpc.CallOption) (*CustomClass, error)
// Get a custom class.
GetCustomClass(ctx context.Context, in *GetCustomClassRequest, opts ...grpc.CallOption) (*CustomClass, error)
// List custom classes.
ListCustomClasses(ctx context.Context, in *ListCustomClassesRequest, opts ...grpc.CallOption) (*ListCustomClassesResponse, error)
// Update a custom class.
UpdateCustomClass(ctx context.Context, in *UpdateCustomClassRequest, opts ...grpc.CallOption) (*CustomClass, error)
// Delete a custom class.
DeleteCustomClass(ctx context.Context, in *DeleteCustomClassRequest, opts ...grpc.CallOption) (*emptypb.Empty, error)
}
AdaptationClient is the client API for Adaptation service.
For semantics around ctx use and closing/ending streaming RPCs, please refer to https://godoc.org/google.golang.org/grpc#ClientConn.NewStream.
func NewAdaptationClient
func NewAdaptationClient(cc grpc.ClientConnInterface) AdaptationClient
AdaptationServer
type AdaptationServer interface {
// Create a set of phrase hints. Each item in the set can be a single word or
// a multi-word phrase. The items in the PhraseSet are favored by the
// recognition model when you send a call that includes the PhraseSet.
CreatePhraseSet(context.Context, *CreatePhraseSetRequest) (*PhraseSet, error)
// Get a phrase set.
GetPhraseSet(context.Context, *GetPhraseSetRequest) (*PhraseSet, error)
// List phrase sets.
ListPhraseSet(context.Context, *ListPhraseSetRequest) (*ListPhraseSetResponse, error)
// Update a phrase set.
UpdatePhraseSet(context.Context, *UpdatePhraseSetRequest) (*PhraseSet, error)
// Delete a phrase set.
DeletePhraseSet(context.Context, *DeletePhraseSetRequest) (*emptypb.Empty, error)
// Create a custom class.
CreateCustomClass(context.Context, *CreateCustomClassRequest) (*CustomClass, error)
// Get a custom class.
GetCustomClass(context.Context, *GetCustomClassRequest) (*CustomClass, error)
// List custom classes.
ListCustomClasses(context.Context, *ListCustomClassesRequest) (*ListCustomClassesResponse, error)
// Update a custom class.
UpdateCustomClass(context.Context, *UpdateCustomClassRequest) (*CustomClass, error)
// Delete a custom class.
DeleteCustomClass(context.Context, *DeleteCustomClassRequest) (*emptypb.Empty, error)
}
AdaptationServer is the server API for Adaptation service.
CreateCustomClassRequest
type CreateCustomClassRequest struct {
// Required. The parent resource where this custom class will be created.
// Format:
//
// `projects/{project}/locations/{location}/customClasses`
//
// Speech-to-Text supports three locations: `global`, `us` (US North America),
// and `eu` (Europe). If you are calling the `speech.googleapis.com`
// endpoint, use the `global` location. To specify a region, use a
// [regional endpoint](https://cloud.google.com/speech-to-text/docs/endpoints)
// with matching `us` or `eu` location value.
Parent string `protobuf:"bytes,1,opt,name=parent,proto3" json:"parent,omitempty"`
// Required. The ID to use for the custom class, which will become the final
// component of the custom class' resource name.
//
// This value should restrict to letters, numbers, and hyphens, with the first
// character a letter, the last a letter or a number, and be 4-63 characters.
CustomClassId string `protobuf:"bytes,2,opt,name=custom_class_id,json=customClassId,proto3" json:"custom_class_id,omitempty"`
// Required. The custom class to create.
CustomClass *CustomClass `protobuf:"bytes,3,opt,name=custom_class,json=customClass,proto3" json:"custom_class,omitempty"`
// contains filtered or unexported fields
}
Message sent by the client for the CreateCustomClass
method.
func (*CreateCustomClassRequest) Descriptor
func (*CreateCustomClassRequest) Descriptor() ([]byte, []int)
Deprecated: Use CreateCustomClassRequest.ProtoReflect.Descriptor instead.
func (*CreateCustomClassRequest) GetCustomClass
func (x *CreateCustomClassRequest) GetCustomClass() *CustomClass
func (*CreateCustomClassRequest) GetCustomClassId
func (x *CreateCustomClassRequest) GetCustomClassId() string
func (*CreateCustomClassRequest) GetParent
func (x *CreateCustomClassRequest) GetParent() string
func (*CreateCustomClassRequest) ProtoMessage
func (*CreateCustomClassRequest) ProtoMessage()
func (*CreateCustomClassRequest) ProtoReflect
func (x *CreateCustomClassRequest) ProtoReflect() protoreflect.Message
func (*CreateCustomClassRequest) Reset
func (x *CreateCustomClassRequest) Reset()
func (*CreateCustomClassRequest) String
func (x *CreateCustomClassRequest) String() string
CreatePhraseSetRequest
type CreatePhraseSetRequest struct {
// Required. The parent resource where this phrase set will be created.
// Format:
//
// `projects/{project}/locations/{location}`
//
// Speech-to-Text supports three locations: `global`, `us` (US North America),
// and `eu` (Europe). If you are calling the `speech.googleapis.com`
// endpoint, use the `global` location. To specify a region, use a
// [regional endpoint](https://cloud.google.com/speech-to-text/docs/endpoints)
// with matching `us` or `eu` location value.
Parent string `protobuf:"bytes,1,opt,name=parent,proto3" json:"parent,omitempty"`
// Required. The ID to use for the phrase set, which will become the final
// component of the phrase set's resource name.
//
// This value should restrict to letters, numbers, and hyphens, with the first
// character a letter, the last a letter or a number, and be 4-63 characters.
PhraseSetId string `protobuf:"bytes,2,opt,name=phrase_set_id,json=phraseSetId,proto3" json:"phrase_set_id,omitempty"`
// Required. The phrase set to create.
PhraseSet *PhraseSet `protobuf:"bytes,3,opt,name=phrase_set,json=phraseSet,proto3" json:"phrase_set,omitempty"`
// contains filtered or unexported fields
}
Message sent by the client for the CreatePhraseSet
method.
func (*CreatePhraseSetRequest) Descriptor
func (*CreatePhraseSetRequest) Descriptor() ([]byte, []int)
Deprecated: Use CreatePhraseSetRequest.ProtoReflect.Descriptor instead.
func (*CreatePhraseSetRequest) GetParent
func (x *CreatePhraseSetRequest) GetParent() string
func (*CreatePhraseSetRequest) GetPhraseSet
func (x *CreatePhraseSetRequest) GetPhraseSet() *PhraseSet
func (*CreatePhraseSetRequest) GetPhraseSetId
func (x *CreatePhraseSetRequest) GetPhraseSetId() string
func (*CreatePhraseSetRequest) ProtoMessage
func (*CreatePhraseSetRequest) ProtoMessage()
func (*CreatePhraseSetRequest) ProtoReflect
func (x *CreatePhraseSetRequest) ProtoReflect() protoreflect.Message
func (*CreatePhraseSetRequest) Reset
func (x *CreatePhraseSetRequest) Reset()
func (*CreatePhraseSetRequest) String
func (x *CreatePhraseSetRequest) String() string
CustomClass
type CustomClass struct {
// The resource name of the custom class.
Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
// If this custom class is a resource, the custom_class_id is the resource id
// of the CustomClass. Case sensitive.
CustomClassId string `protobuf:"bytes,2,opt,name=custom_class_id,json=customClassId,proto3" json:"custom_class_id,omitempty"`
// A collection of class items.
Items []*CustomClass_ClassItem `protobuf:"bytes,3,rep,name=items,proto3" json:"items,omitempty"`
// contains filtered or unexported fields
}
A set of words or phrases that represents a common concept likely to appear in your audio, for example a list of passenger ship names. CustomClass items can be substituted into placeholders that you set in PhraseSet phrases.
func (*CustomClass) Descriptor
func (*CustomClass) Descriptor() ([]byte, []int)
Deprecated: Use CustomClass.ProtoReflect.Descriptor instead.
func (*CustomClass) GetCustomClassId
func (x *CustomClass) GetCustomClassId() string
func (*CustomClass) GetItems
func (x *CustomClass) GetItems() []*CustomClass_ClassItem
func (*CustomClass) GetName
func (x *CustomClass) GetName() string
func (*CustomClass) ProtoMessage
func (*CustomClass) ProtoMessage()
func (*CustomClass) ProtoReflect
func (x *CustomClass) ProtoReflect() protoreflect.Message
func (*CustomClass) Reset
func (x *CustomClass) Reset()
func (*CustomClass) String
func (x *CustomClass) String() string
CustomClass_ClassItem
type CustomClass_ClassItem struct {
// The class item's value.
Value string `protobuf:"bytes,1,opt,name=value,proto3" json:"value,omitempty"`
// contains filtered or unexported fields
}
An item of the class.
func (*CustomClass_ClassItem) Descriptor
func (*CustomClass_ClassItem) Descriptor() ([]byte, []int)
Deprecated: Use CustomClass_ClassItem.ProtoReflect.Descriptor instead.
func (*CustomClass_ClassItem) GetValue
func (x *CustomClass_ClassItem) GetValue() string
func (*CustomClass_ClassItem) ProtoMessage
func (*CustomClass_ClassItem) ProtoMessage()
func (*CustomClass_ClassItem) ProtoReflect
func (x *CustomClass_ClassItem) ProtoReflect() protoreflect.Message
func (*CustomClass_ClassItem) Reset
func (x *CustomClass_ClassItem) Reset()
func (*CustomClass_ClassItem) String
func (x *CustomClass_ClassItem) String() string
DeleteCustomClassRequest
type DeleteCustomClassRequest struct {
// Required. The name of the custom class to delete. Format:
//
// `projects/{project}/locations/{location}/customClasses/{custom_class}`
//
// Speech-to-Text supports three locations: `global`, `us` (US North America),
// and `eu` (Europe). If you are calling the `speech.googleapis.com`
// endpoint, use the `global` location. To specify a region, use a
// [regional endpoint](https://cloud.google.com/speech-to-text/docs/endpoints)
// with matching `us` or `eu` location value.
Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
// contains filtered or unexported fields
}
Message sent by the client for the DeleteCustomClass
method.
func (*DeleteCustomClassRequest) Descriptor
func (*DeleteCustomClassRequest) Descriptor() ([]byte, []int)
Deprecated: Use DeleteCustomClassRequest.ProtoReflect.Descriptor instead.
func (*DeleteCustomClassRequest) GetName
func (x *DeleteCustomClassRequest) GetName() string
func (*DeleteCustomClassRequest) ProtoMessage
func (*DeleteCustomClassRequest) ProtoMessage()
func (*DeleteCustomClassRequest) ProtoReflect
func (x *DeleteCustomClassRequest) ProtoReflect() protoreflect.Message
func (*DeleteCustomClassRequest) Reset
func (x *DeleteCustomClassRequest) Reset()
func (*DeleteCustomClassRequest) String
func (x *DeleteCustomClassRequest) String() string
DeletePhraseSetRequest
type DeletePhraseSetRequest struct {
// Required. The name of the phrase set to delete. Format:
//
// `projects/{project}/locations/{location}/phraseSets/{phrase_set}`
Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
// contains filtered or unexported fields
}
Message sent by the client for the DeletePhraseSet
method.
func (*DeletePhraseSetRequest) Descriptor
func (*DeletePhraseSetRequest) Descriptor() ([]byte, []int)
Deprecated: Use DeletePhraseSetRequest.ProtoReflect.Descriptor instead.
func (*DeletePhraseSetRequest) GetName
func (x *DeletePhraseSetRequest) GetName() string
func (*DeletePhraseSetRequest) ProtoMessage
func (*DeletePhraseSetRequest) ProtoMessage()
func (*DeletePhraseSetRequest) ProtoReflect
func (x *DeletePhraseSetRequest) ProtoReflect() protoreflect.Message
func (*DeletePhraseSetRequest) Reset
func (x *DeletePhraseSetRequest) Reset()
func (*DeletePhraseSetRequest) String
func (x *DeletePhraseSetRequest) String() string
GetCustomClassRequest
type GetCustomClassRequest struct {
// Required. The name of the custom class to retrieve. Format:
//
// `projects/{project}/locations/{location}/customClasses/{custom_class}`
Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
// contains filtered or unexported fields
}
Message sent by the client for the GetCustomClass
method.
func (*GetCustomClassRequest) Descriptor
func (*GetCustomClassRequest) Descriptor() ([]byte, []int)
Deprecated: Use GetCustomClassRequest.ProtoReflect.Descriptor instead.
func (*GetCustomClassRequest) GetName
func (x *GetCustomClassRequest) GetName() string
func (*GetCustomClassRequest) ProtoMessage
func (*GetCustomClassRequest) ProtoMessage()
func (*GetCustomClassRequest) ProtoReflect
func (x *GetCustomClassRequest) ProtoReflect() protoreflect.Message
func (*GetCustomClassRequest) Reset
func (x *GetCustomClassRequest) Reset()
func (*GetCustomClassRequest) String
func (x *GetCustomClassRequest) String() string
GetPhraseSetRequest
type GetPhraseSetRequest struct {
// Required. The name of the phrase set to retrieve. Format:
//
// `projects/{project}/locations/{location}/phraseSets/{phrase_set}`
//
// Speech-to-Text supports three locations: `global`, `us` (US North America),
// and `eu` (Europe). If you are calling the `speech.googleapis.com`
// endpoint, use the `global` location. To specify a region, use a
// [regional endpoint](https://cloud.google.com/speech-to-text/docs/endpoints)
// with matching `us` or `eu` location value.
Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
// contains filtered or unexported fields
}
Message sent by the client for the GetPhraseSet
method.
func (*GetPhraseSetRequest) Descriptor
func (*GetPhraseSetRequest) Descriptor() ([]byte, []int)
Deprecated: Use GetPhraseSetRequest.ProtoReflect.Descriptor instead.
func (*GetPhraseSetRequest) GetName
func (x *GetPhraseSetRequest) GetName() string
func (*GetPhraseSetRequest) ProtoMessage
func (*GetPhraseSetRequest) ProtoMessage()
func (*GetPhraseSetRequest) ProtoReflect
func (x *GetPhraseSetRequest) ProtoReflect() protoreflect.Message
func (*GetPhraseSetRequest) Reset
func (x *GetPhraseSetRequest) Reset()
func (*GetPhraseSetRequest) String
func (x *GetPhraseSetRequest) String() string
ListCustomClassesRequest
type ListCustomClassesRequest struct {
// Required. The parent, which owns this collection of custom classes. Format:
//
// `projects/{project}/locations/{location}/customClasses`
//
// Speech-to-Text supports three locations: `global`, `us` (US North America),
// and `eu` (Europe). If you are calling the `speech.googleapis.com`
// endpoint, use the `global` location. To specify a region, use a
// [regional endpoint](https://cloud.google.com/speech-to-text/docs/endpoints)
// with matching `us` or `eu` location value.
Parent string `protobuf:"bytes,1,opt,name=parent,proto3" json:"parent,omitempty"`
// The maximum number of custom classes to return. The service may return
// fewer than this value. If unspecified, at most 50 custom classes will be
// returned. The maximum value is 1000; values above 1000 will be coerced to
// 1000.
PageSize int32 `protobuf:"varint,2,opt,name=page_size,json=pageSize,proto3" json:"page_size,omitempty"`
// A page token, received from a previous `ListCustomClass` call.
// Provide this to retrieve the subsequent page.
//
// When paginating, all other parameters provided to `ListCustomClass` must
// match the call that provided the page token.
PageToken string `protobuf:"bytes,3,opt,name=page_token,json=pageToken,proto3" json:"page_token,omitempty"`
// contains filtered or unexported fields
}
Message sent by the client for the ListCustomClasses
method.
func (*ListCustomClassesRequest) Descriptor
func (*ListCustomClassesRequest) Descriptor() ([]byte, []int)
Deprecated: Use ListCustomClassesRequest.ProtoReflect.Descriptor instead.
func (*ListCustomClassesRequest) GetPageSize
func (x *ListCustomClassesRequest) GetPageSize() int32
func (*ListCustomClassesRequest) GetPageToken
func (x *ListCustomClassesRequest) GetPageToken() string
func (*ListCustomClassesRequest) GetParent
func (x *ListCustomClassesRequest) GetParent() string
func (*ListCustomClassesRequest) ProtoMessage
func (*ListCustomClassesRequest) ProtoMessage()
func (*ListCustomClassesRequest) ProtoReflect
func (x *ListCustomClassesRequest) ProtoReflect() protoreflect.Message
func (*ListCustomClassesRequest) Reset
func (x *ListCustomClassesRequest) Reset()
func (*ListCustomClassesRequest) String
func (x *ListCustomClassesRequest) String() string
ListCustomClassesResponse
type ListCustomClassesResponse struct {
// The custom classes.
CustomClasses []*CustomClass `protobuf:"bytes,1,rep,name=custom_classes,json=customClasses,proto3" json:"custom_classes,omitempty"`
// A token, which can be sent as `page_token` to retrieve the next page.
// If this field is omitted, there are no subsequent pages.
NextPageToken string `protobuf:"bytes,2,opt,name=next_page_token,json=nextPageToken,proto3" json:"next_page_token,omitempty"`
// contains filtered or unexported fields
}
Message returned to the client by the ListCustomClasses
method.
func (*ListCustomClassesResponse) Descriptor
func (*ListCustomClassesResponse) Descriptor() ([]byte, []int)
Deprecated: Use ListCustomClassesResponse.ProtoReflect.Descriptor instead.
func (*ListCustomClassesResponse) GetCustomClasses
func (x *ListCustomClassesResponse) GetCustomClasses() []*CustomClass
func (*ListCustomClassesResponse) GetNextPageToken
func (x *ListCustomClassesResponse) GetNextPageToken() string
func (*ListCustomClassesResponse) ProtoMessage
func (*ListCustomClassesResponse) ProtoMessage()
func (*ListCustomClassesResponse) ProtoReflect
func (x *ListCustomClassesResponse) ProtoReflect() protoreflect.Message
func (*ListCustomClassesResponse) Reset
func (x *ListCustomClassesResponse) Reset()
func (*ListCustomClassesResponse) String
func (x *ListCustomClassesResponse) String() string
ListPhraseSetRequest
type ListPhraseSetRequest struct {
// Required. The parent, which owns this collection of phrase set. Format:
//
// `projects/{project}/locations/{location}`
//
// Speech-to-Text supports three locations: `global`, `us` (US North America),
// and `eu` (Europe). If you are calling the `speech.googleapis.com`
// endpoint, use the `global` location. To specify a region, use a
// [regional endpoint](https://cloud.google.com/speech-to-text/docs/endpoints)
// with matching `us` or `eu` location value.
Parent string `protobuf:"bytes,1,opt,name=parent,proto3" json:"parent,omitempty"`
// The maximum number of phrase sets to return. The service may return
// fewer than this value. If unspecified, at most 50 phrase sets will be
// returned. The maximum value is 1000; values above 1000 will be coerced to
// 1000.
PageSize int32 `protobuf:"varint,2,opt,name=page_size,json=pageSize,proto3" json:"page_size,omitempty"`
// A page token, received from a previous `ListPhraseSet` call.
// Provide this to retrieve the subsequent page.
//
// When paginating, all other parameters provided to `ListPhraseSet` must
// match the call that provided the page token.
PageToken string `protobuf:"bytes,3,opt,name=page_token,json=pageToken,proto3" json:"page_token,omitempty"`
// contains filtered or unexported fields
}
Message sent by the client for the ListPhraseSet
method.
func (*ListPhraseSetRequest) Descriptor
func (*ListPhraseSetRequest) Descriptor() ([]byte, []int)
Deprecated: Use ListPhraseSetRequest.ProtoReflect.Descriptor instead.
func (*ListPhraseSetRequest) GetPageSize
func (x *ListPhraseSetRequest) GetPageSize() int32
func (*ListPhraseSetRequest) GetPageToken
func (x *ListPhraseSetRequest) GetPageToken() string
func (*ListPhraseSetRequest) GetParent
func (x *ListPhraseSetRequest) GetParent() string
func (*ListPhraseSetRequest) ProtoMessage
func (*ListPhraseSetRequest) ProtoMessage()
func (*ListPhraseSetRequest) ProtoReflect
func (x *ListPhraseSetRequest) ProtoReflect() protoreflect.Message
func (*ListPhraseSetRequest) Reset
func (x *ListPhraseSetRequest) Reset()
func (*ListPhraseSetRequest) String
func (x *ListPhraseSetRequest) String() string
ListPhraseSetResponse
type ListPhraseSetResponse struct {
// The phrase set.
PhraseSets []*PhraseSet `protobuf:"bytes,1,rep,name=phrase_sets,json=phraseSets,proto3" json:"phrase_sets,omitempty"`
// A token, which can be sent as `page_token` to retrieve the next page.
// If this field is omitted, there are no subsequent pages.
NextPageToken string `protobuf:"bytes,2,opt,name=next_page_token,json=nextPageToken,proto3" json:"next_page_token,omitempty"`
// contains filtered or unexported fields
}
Message returned to the client by the ListPhraseSet
method.
func (*ListPhraseSetResponse) Descriptor
func (*ListPhraseSetResponse) Descriptor() ([]byte, []int)
Deprecated: Use ListPhraseSetResponse.ProtoReflect.Descriptor instead.
func (*ListPhraseSetResponse) GetNextPageToken
func (x *ListPhraseSetResponse) GetNextPageToken() string
func (*ListPhraseSetResponse) GetPhraseSets
func (x *ListPhraseSetResponse) GetPhraseSets() []*PhraseSet
func (*ListPhraseSetResponse) ProtoMessage
func (*ListPhraseSetResponse) ProtoMessage()
func (*ListPhraseSetResponse) ProtoReflect
func (x *ListPhraseSetResponse) ProtoReflect() protoreflect.Message
func (*ListPhraseSetResponse) Reset
func (x *ListPhraseSetResponse) Reset()
func (*ListPhraseSetResponse) String
func (x *ListPhraseSetResponse) String() string
LongRunningRecognizeMetadata
type LongRunningRecognizeMetadata struct {
// Approximate percentage of audio processed thus far. Guaranteed to be 100
// when the audio is fully processed and the results are available.
ProgressPercent int32 `protobuf:"varint,1,opt,name=progress_percent,json=progressPercent,proto3" json:"progress_percent,omitempty"`
// Time when the request was received.
StartTime *timestamppb.Timestamp `protobuf:"bytes,2,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
// Time of the most recent processing update.
LastUpdateTime *timestamppb.Timestamp `protobuf:"bytes,3,opt,name=last_update_time,json=lastUpdateTime,proto3" json:"last_update_time,omitempty"`
// Output only. The URI of the audio file being transcribed. Empty if the
// audio was sent as byte content.
Uri string `protobuf:"bytes,4,opt,name=uri,proto3" json:"uri,omitempty"`
// contains filtered or unexported fields
}
Describes the progress of a long-running LongRunningRecognize
call. It is
included in the metadata
field of the Operation
returned by the
GetOperation
call of the google::longrunning::Operations
service.
func (*LongRunningRecognizeMetadata) Descriptor
func (*LongRunningRecognizeMetadata) Descriptor() ([]byte, []int)
Deprecated: Use LongRunningRecognizeMetadata.ProtoReflect.Descriptor instead.
func (*LongRunningRecognizeMetadata) GetLastUpdateTime
func (x *LongRunningRecognizeMetadata) GetLastUpdateTime() *timestamppb.Timestamp
func (*LongRunningRecognizeMetadata) GetProgressPercent
func (x *LongRunningRecognizeMetadata) GetProgressPercent() int32
func (*LongRunningRecognizeMetadata) GetStartTime
func (x *LongRunningRecognizeMetadata) GetStartTime() *timestamppb.Timestamp
func (*LongRunningRecognizeMetadata) GetUri
func (x *LongRunningRecognizeMetadata) GetUri() string
func (*LongRunningRecognizeMetadata) ProtoMessage
func (*LongRunningRecognizeMetadata) ProtoMessage()
func (*LongRunningRecognizeMetadata) ProtoReflect
func (x *LongRunningRecognizeMetadata) ProtoReflect() protoreflect.Message
func (*LongRunningRecognizeMetadata) Reset
func (x *LongRunningRecognizeMetadata) Reset()
func (*LongRunningRecognizeMetadata) String
func (x *LongRunningRecognizeMetadata) String() string
LongRunningRecognizeRequest
type LongRunningRecognizeRequest struct {
// Required. Provides information to the recognizer that specifies how to
// process the request.
Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config,proto3" json:"config,omitempty"`
// Required. The audio data to be recognized.
Audio *RecognitionAudio `protobuf:"bytes,2,opt,name=audio,proto3" json:"audio,omitempty"`
// Optional. Specifies an optional destination for the recognition results.
OutputConfig *TranscriptOutputConfig `protobuf:"bytes,4,opt,name=output_config,json=outputConfig,proto3" json:"output_config,omitempty"`
// contains filtered or unexported fields
}
The top-level message sent by the client for the LongRunningRecognize
method.
func (*LongRunningRecognizeRequest) Descriptor
func (*LongRunningRecognizeRequest) Descriptor() ([]byte, []int)
Deprecated: Use LongRunningRecognizeRequest.ProtoReflect.Descriptor instead.
func (*LongRunningRecognizeRequest) GetAudio
func (x *LongRunningRecognizeRequest) GetAudio() *RecognitionAudio
func (*LongRunningRecognizeRequest) GetConfig
func (x *LongRunningRecognizeRequest) GetConfig() *RecognitionConfig
func (*LongRunningRecognizeRequest) GetOutputConfig
func (x *LongRunningRecognizeRequest) GetOutputConfig() *TranscriptOutputConfig
func (*LongRunningRecognizeRequest) ProtoMessage
func (*LongRunningRecognizeRequest) ProtoMessage()
func (*LongRunningRecognizeRequest) ProtoReflect
func (x *LongRunningRecognizeRequest) ProtoReflect() protoreflect.Message
func (*LongRunningRecognizeRequest) Reset
func (x *LongRunningRecognizeRequest) Reset()
func (*LongRunningRecognizeRequest) String
func (x *LongRunningRecognizeRequest) String() string
LongRunningRecognizeResponse
type LongRunningRecognizeResponse struct {
// Sequential list of transcription results corresponding to
// sequential portions of audio.
Results []*SpeechRecognitionResult `protobuf:"bytes,2,rep,name=results,proto3" json:"results,omitempty"`
// When available, billed audio seconds for the corresponding request.
TotalBilledTime *durationpb.Duration `protobuf:"bytes,3,opt,name=total_billed_time,json=totalBilledTime,proto3" json:"total_billed_time,omitempty"`
// Original output config if present in the request.
OutputConfig *TranscriptOutputConfig `protobuf:"bytes,6,opt,name=output_config,json=outputConfig,proto3" json:"output_config,omitempty"`
// If the transcript output fails this field contains the relevant error.
OutputError *status.Status `protobuf:"bytes,7,opt,name=output_error,json=outputError,proto3" json:"output_error,omitempty"`
// Provides information on speech adaptation behavior in response
SpeechAdaptationInfo *SpeechAdaptationInfo `protobuf:"bytes,8,opt,name=speech_adaptation_info,json=speechAdaptationInfo,proto3" json:"speech_adaptation_info,omitempty"`
// The ID associated with the request. This is a unique ID specific only to
// the given request.
RequestId int64 `protobuf:"varint,9,opt,name=request_id,json=requestId,proto3" json:"request_id,omitempty"`
// contains filtered or unexported fields
}
The only message returned to the client by the LongRunningRecognize
method.
It contains the result as zero or more sequential SpeechRecognitionResult
messages. It is included in the result.response
field of the Operation
returned by the GetOperation
call of the google::longrunning::Operations
service.
func (*LongRunningRecognizeResponse) Descriptor
func (*LongRunningRecognizeResponse) Descriptor() ([]byte, []int)
Deprecated: Use LongRunningRecognizeResponse.ProtoReflect.Descriptor instead.
func (*LongRunningRecognizeResponse) GetOutputConfig
func (x *LongRunningRecognizeResponse) GetOutputConfig() *TranscriptOutputConfig
func (*LongRunningRecognizeResponse) GetOutputError
func (x *LongRunningRecognizeResponse) GetOutputError() *status.Status
func (*LongRunningRecognizeResponse) GetRequestId
func (x *LongRunningRecognizeResponse) GetRequestId() int64
func (*LongRunningRecognizeResponse) GetResults
func (x *LongRunningRecognizeResponse) GetResults() []*SpeechRecognitionResult
func (*LongRunningRecognizeResponse) GetSpeechAdaptationInfo
func (x *LongRunningRecognizeResponse) GetSpeechAdaptationInfo() *SpeechAdaptationInfo
func (*LongRunningRecognizeResponse) GetTotalBilledTime
func (x *LongRunningRecognizeResponse) GetTotalBilledTime() *durationpb.Duration
func (*LongRunningRecognizeResponse) ProtoMessage
func (*LongRunningRecognizeResponse) ProtoMessage()
func (*LongRunningRecognizeResponse) ProtoReflect
func (x *LongRunningRecognizeResponse) ProtoReflect() protoreflect.Message
func (*LongRunningRecognizeResponse) Reset
func (x *LongRunningRecognizeResponse) Reset()
func (*LongRunningRecognizeResponse) String
func (x *LongRunningRecognizeResponse) String() string
PhraseSet
type PhraseSet struct {
// The resource name of the phrase set.
Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
// A list of word and phrases.
Phrases []*PhraseSet_Phrase `protobuf:"bytes,2,rep,name=phrases,proto3" json:"phrases,omitempty"`
// Hint Boost. Positive value will increase the probability that a specific
// phrase will be recognized over other similar sounding phrases. The higher
// the boost, the higher the chance of false positive recognition as well.
// Negative boost values would correspond to anti-biasing. Anti-biasing is not
// enabled, so negative boost will simply be ignored. Though `boost` can
// accept a wide range of positive values, most use cases are best served with
// values between 0 (exclusive) and 20. We recommend using a binary search
// approach to finding the optimal value for your use case as well as adding
// phrases both with and without boost to your requests.
Boost float32 `protobuf:"fixed32,4,opt,name=boost,proto3" json:"boost,omitempty"`
// contains filtered or unexported fields
}
Provides "hints" to the speech recognizer to favor specific words and phrases in the results.
func (*PhraseSet) Descriptor
Deprecated: Use PhraseSet.ProtoReflect.Descriptor instead.
func (*PhraseSet) GetBoost
func (*PhraseSet) GetName
func (*PhraseSet) GetPhrases
func (x *PhraseSet) GetPhrases() []*PhraseSet_Phrase
func (*PhraseSet) ProtoMessage
func (*PhraseSet) ProtoMessage()
func (*PhraseSet) ProtoReflect
func (x *PhraseSet) ProtoReflect() protoreflect.Message
func (*PhraseSet) Reset
func (x *PhraseSet) Reset()
func (*PhraseSet) String
PhraseSet_Phrase
type PhraseSet_Phrase struct {
// The phrase itself.
Value string `protobuf:"bytes,1,opt,name=value,proto3" json:"value,omitempty"`
// Hint Boost. Overrides the boost set at the phrase set level.
// Positive value will increase the probability that a specific phrase will
// be recognized over other similar sounding phrases. The higher the boost,
// the higher the chance of false positive recognition as well. Negative
// boost will simply be ignored. Though `boost` can accept a wide range of
// positive values, most use cases are best served
// with values between 0 and 20. We recommend using a binary search approach
// to finding the optimal value for your use case as well as adding
// phrases both with and without boost to your requests.
Boost float32 `protobuf:"fixed32,2,opt,name=boost,proto3" json:"boost,omitempty"`
// contains filtered or unexported fields
}
A phrases containing words and phrase "hints" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See usage limits.
List items can also include pre-built or custom classes containing groups
of words that represent common concepts that occur in natural language. For
example, rather than providing a phrase hint for every month of the
year (e.g. "i was born in january", "i was born in febuary", ...), use the
pre-built $MONTH
class improves the likelihood of correctly transcribing
audio that includes months (e.g. "i was born in $month").
To refer to pre-built classes, use the class' symbol prepended with $
e.g. $MONTH
. To refer to custom classes that were defined inline in the
request, set the class's custom_class_id
to a string unique to all class
resources and inline classes. Then use the class' id wrapped in ${...}
e.g. "${my-months}". To refer to custom classes resources, use the class'
id wrapped in ${}
(e.g. ${my-months}
).
Speech-to-Text supports three locations: global
, us
(US North America),
and eu
(Europe). If you are calling the speech.googleapis.com
endpoint, use the global
location. To specify a region, use a
regional endpoint
with matching us
or eu
location value.
func (*PhraseSet_Phrase) Descriptor
func (*PhraseSet_Phrase) Descriptor() ([]byte, []int)
Deprecated: Use PhraseSet_Phrase.ProtoReflect.Descriptor instead.
func (*PhraseSet_Phrase) GetBoost
func (x *PhraseSet_Phrase) GetBoost() float32
func (*PhraseSet_Phrase) GetValue
func (x *PhraseSet_Phrase) GetValue() string
func (*PhraseSet_Phrase) ProtoMessage
func (*PhraseSet_Phrase) ProtoMessage()
func (*PhraseSet_Phrase) ProtoReflect
func (x *PhraseSet_Phrase) ProtoReflect() protoreflect.Message
func (*PhraseSet_Phrase) Reset
func (x *PhraseSet_Phrase) Reset()
func (*PhraseSet_Phrase) String
func (x *PhraseSet_Phrase) String() string
RecognitionAudio
type RecognitionAudio struct {
// The audio source, which is either inline content or a Google Cloud
// Storage uri.
//
// Types that are assignable to AudioSource:
// *RecognitionAudio_Content
// *RecognitionAudio_Uri
AudioSource isRecognitionAudio_AudioSource `protobuf_oneof:"audio_source"`
// contains filtered or unexported fields
}
Contains audio data in the encoding specified in the RecognitionConfig
.
Either content
or uri
must be supplied. Supplying both or neither
returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
See content limits.
func (*RecognitionAudio) Descriptor
func (*RecognitionAudio) Descriptor() ([]byte, []int)
Deprecated: Use RecognitionAudio.ProtoReflect.Descriptor instead.
func (*RecognitionAudio) GetAudioSource
func (m *RecognitionAudio) GetAudioSource() isRecognitionAudio_AudioSource
func (*RecognitionAudio) GetContent
func (x *RecognitionAudio) GetContent() []byte
func (*RecognitionAudio) GetUri
func (x *RecognitionAudio) GetUri() string
func (*RecognitionAudio) ProtoMessage
func (*RecognitionAudio) ProtoMessage()
func (*RecognitionAudio) ProtoReflect
func (x *RecognitionAudio) ProtoReflect() protoreflect.Message
func (*RecognitionAudio) Reset
func (x *RecognitionAudio) Reset()
func (*RecognitionAudio) String
func (x *RecognitionAudio) String() string
RecognitionAudio_Content
type RecognitionAudio_Content struct {
// The audio data bytes encoded as specified in
// `RecognitionConfig`. Note: as with all bytes fields, proto buffers use a
// pure binary representation, whereas JSON representations use base64.
Content []byte `protobuf:"bytes,1,opt,name=content,proto3,oneof"`
}
RecognitionAudio_Uri
type RecognitionAudio_Uri struct {
// URI that points to a file that contains audio data bytes as specified in
// `RecognitionConfig`. The file must not be compressed (for example, gzip).
// Currently, only Google Cloud Storage URIs are
// supported, which must be specified in the following format:
// `gs://bucket_name/object_name` (other URI formats return
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
// For more information, see [Request
// URIs](https://cloud.google.com/storage/docs/reference-uris).
Uri string `protobuf:"bytes,2,opt,name=uri,proto3,oneof"`
}
RecognitionConfig
type RecognitionConfig struct {
Encoding RecognitionConfig_AudioEncoding "" /* 130 byte string literal not displayed */
SampleRateHertz int32 `protobuf:"varint,2,opt,name=sample_rate_hertz,json=sampleRateHertz,proto3" json:"sample_rate_hertz,omitempty"`
AudioChannelCount int32 `protobuf:"varint,7,opt,name=audio_channel_count,json=audioChannelCount,proto3" json:"audio_channel_count,omitempty"`
EnableSeparateRecognitionPerChannel bool "" /* 174 byte string literal not displayed */
LanguageCode string `protobuf:"bytes,3,opt,name=language_code,json=languageCode,proto3" json:"language_code,omitempty"`
AlternativeLanguageCodes []string "" /* 136 byte string literal not displayed */
MaxAlternatives int32 `protobuf:"varint,4,opt,name=max_alternatives,json=maxAlternatives,proto3" json:"max_alternatives,omitempty"`
ProfanityFilter bool `protobuf:"varint,5,opt,name=profanity_filter,json=profanityFilter,proto3" json:"profanity_filter,omitempty"`
Adaptation *SpeechAdaptation `protobuf:"bytes,20,opt,name=adaptation,proto3" json:"adaptation,omitempty"`
SpeechContexts []*SpeechContext `protobuf:"bytes,6,rep,name=speech_contexts,json=speechContexts,proto3" json:"speech_contexts,omitempty"`
EnableWordTimeOffsets bool "" /* 129 byte string literal not displayed */
EnableWordConfidence bool `protobuf:"varint,15,opt,name=enable_word_confidence,json=enableWordConfidence,proto3" json:"enable_word_confidence,omitempty"`
EnableAutomaticPunctuation bool "" /* 143 byte string literal not displayed */
EnableSpokenPunctuation *wrapperspb.BoolValue "" /* 133 byte string literal not displayed */
EnableSpokenEmojis *wrapperspb.BoolValue `protobuf:"bytes,23,opt,name=enable_spoken_emojis,json=enableSpokenEmojis,proto3" json:"enable_spoken_emojis,omitempty"`
DiarizationConfig *SpeakerDiarizationConfig `protobuf:"bytes,19,opt,name=diarization_config,json=diarizationConfig,proto3" json:"diarization_config,omitempty"`
Metadata *RecognitionMetadata `protobuf:"bytes,9,opt,name=metadata,proto3" json:"metadata,omitempty"`
Model string `protobuf:"bytes,13,opt,name=model,proto3" json:"model,omitempty"`
UseEnhanced bool `protobuf:"varint,14,opt,name=use_enhanced,json=useEnhanced,proto3" json:"use_enhanced,omitempty"`
}
Provides information to the recognizer that specifies how to process the request.
func (*RecognitionConfig) Descriptor
func (*RecognitionConfig) Descriptor() ([]byte, []int)
Deprecated: Use RecognitionConfig.ProtoReflect.Descriptor instead.
func (*RecognitionConfig) GetAdaptation
func (x *RecognitionConfig) GetAdaptation() *SpeechAdaptation
func (*RecognitionConfig) GetAlternativeLanguageCodes
func (x *RecognitionConfig) GetAlternativeLanguageCodes() []string
func (*RecognitionConfig) GetAudioChannelCount
func (x *RecognitionConfig) GetAudioChannelCount() int32
func (*RecognitionConfig) GetDiarizationConfig
func (x *RecognitionConfig) GetDiarizationConfig() *SpeakerDiarizationConfig
func (*RecognitionConfig) GetEnableAutomaticPunctuation
func (x *RecognitionConfig) GetEnableAutomaticPunctuation() bool
func (*RecognitionConfig) GetEnableSeparateRecognitionPerChannel
func (x *RecognitionConfig) GetEnableSeparateRecognitionPerChannel() bool
func (*RecognitionConfig) GetEnableSpokenEmojis
func (x *RecognitionConfig) GetEnableSpokenEmojis() *wrapperspb.BoolValue
func (*RecognitionConfig) GetEnableSpokenPunctuation
func (x *RecognitionConfig) GetEnableSpokenPunctuation() *wrapperspb.BoolValue
func (*RecognitionConfig) GetEnableWordConfidence
func (x *RecognitionConfig) GetEnableWordConfidence() bool
func (*RecognitionConfig) GetEnableWordTimeOffsets
func (x *RecognitionConfig) GetEnableWordTimeOffsets() bool
func (*RecognitionConfig) GetEncoding
func (x *RecognitionConfig) GetEncoding() RecognitionConfig_AudioEncoding
func (*RecognitionConfig) GetLanguageCode
func (x *RecognitionConfig) GetLanguageCode() string
func (*RecognitionConfig) GetMaxAlternatives
func (x *RecognitionConfig) GetMaxAlternatives() int32
func (*RecognitionConfig) GetMetadata
func (x *RecognitionConfig) GetMetadata() *RecognitionMetadata
func (*RecognitionConfig) GetModel
func (x *RecognitionConfig) GetModel() string
func (*RecognitionConfig) GetProfanityFilter
func (x *RecognitionConfig) GetProfanityFilter() bool
func (*RecognitionConfig) GetSampleRateHertz
func (x *RecognitionConfig) GetSampleRateHertz() int32
func (*RecognitionConfig) GetSpeechContexts
func (x *RecognitionConfig) GetSpeechContexts() []*SpeechContext
func (*RecognitionConfig) GetUseEnhanced
func (x *RecognitionConfig) GetUseEnhanced() bool
func (*RecognitionConfig) ProtoMessage
func (*RecognitionConfig) ProtoMessage()
func (*RecognitionConfig) ProtoReflect
func (x *RecognitionConfig) ProtoReflect() protoreflect.Message
func (*RecognitionConfig) Reset
func (x *RecognitionConfig) Reset()
func (*RecognitionConfig) String
func (x *RecognitionConfig) String() string
RecognitionConfig_AudioEncoding
type RecognitionConfig_AudioEncoding int32
The encoding of the audio data sent in the request.
All encodings support only 1 channel (mono) audio, unless the
audio_channel_count
and enable_separate_recognition_per_channel
fields
are set.
For best results, the audio source should be captured and transmitted using
a lossless encoding (FLAC
or LINEAR16
). The accuracy of the speech
recognition can be reduced if lossy codecs are used to capture or transmit
audio, particularly if background noise is present. Lossy codecs include
MULAW
, AMR
, AMR_WB
, OGG_OPUS
, SPEEX_WITH_HEADER_BYTE
, MP3
,
and WEBM_OPUS
.
The FLAC
and WAV
audio file formats include a header that describes the
included audio content. You can request recognition for WAV
files that
contain either LINEAR16
or MULAW
encoded audio.
If you send FLAC
or WAV
audio file format in
your request, you do not need to specify an AudioEncoding
; the audio
encoding format is determined from the file header. If you specify
an AudioEncoding
when you send send FLAC
or WAV
audio, the
encoding configuration must match the encoding described in the audio
header; otherwise the request returns an
[google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
code.
RecognitionConfig_ENCODING_UNSPECIFIED, RecognitionConfig_LINEAR16, RecognitionConfig_FLAC, RecognitionConfig_MULAW, RecognitionConfig_AMR, RecognitionConfig_AMR_WB, RecognitionConfig_OGG_OPUS, RecognitionConfig_SPEEX_WITH_HEADER_BYTE, RecognitionConfig_WEBM_OPUS
const (
// Not specified.
RecognitionConfig_ENCODING_UNSPECIFIED RecognitionConfig_AudioEncoding = 0
// Uncompressed 16-bit signed little-endian samples (Linear PCM).
RecognitionConfig_LINEAR16 RecognitionConfig_AudioEncoding = 1
// `FLAC` (Free Lossless Audio
// Codec) is the recommended encoding because it is
// lossless--therefore recognition is not compromised--and
// requires only about half the bandwidth of `LINEAR16`. `FLAC` stream
// encoding supports 16-bit and 24-bit samples, however, not all fields in
// `STREAMINFO` are supported.
RecognitionConfig_FLAC RecognitionConfig_AudioEncoding = 2
// 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
RecognitionConfig_MULAW RecognitionConfig_AudioEncoding = 3
// Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.
RecognitionConfig_AMR RecognitionConfig_AudioEncoding = 4
// Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.
RecognitionConfig_AMR_WB RecognitionConfig_AudioEncoding = 5
// Opus encoded audio frames in Ogg container
// ([OggOpus](https://wiki.xiph.org/OggOpus)).
// `sample_rate_hertz` must be one of 8000, 12000, 16000, 24000, or 48000.
RecognitionConfig_OGG_OPUS RecognitionConfig_AudioEncoding = 6
// Although the use of lossy encodings is not recommended, if a very low
// bitrate encoding is required, `OGG_OPUS` is highly preferred over
// Speex encoding. The [Speex](https://speex.org/) encoding supported by
// Cloud Speech API has a header byte in each block, as in MIME type
// `audio/x-speex-with-header-byte`.
// It is a variant of the RTP Speex encoding defined in
// [RFC 5574](https://tools.ietf.org/html/rfc5574).
// The stream is a sequence of blocks, one block per RTP packet. Each block
// starts with a byte containing the length of the block, in bytes, followed
// by one or more frames of Speex data, padded to an integral number of
// bytes (octets) as specified in RFC 5574. In other words, each RTP header
// is replaced with a single byte containing the block length. Only Speex
// wideband is supported. `sample_rate_hertz` must be 16000.
RecognitionConfig_SPEEX_WITH_HEADER_BYTE RecognitionConfig_AudioEncoding = 7
// Opus encoded audio frames in WebM container
// ([OggOpus](https://wiki.xiph.org/OggOpus)). `sample_rate_hertz` must be
// one of 8000, 12000, 16000, 24000, or 48000.
RecognitionConfig_WEBM_OPUS RecognitionConfig_AudioEncoding = 9
)
func (RecognitionConfig_AudioEncoding) Descriptor
func (RecognitionConfig_AudioEncoding) Descriptor() protoreflect.EnumDescriptor
func (RecognitionConfig_AudioEncoding) Enum
func (x RecognitionConfig_AudioEncoding) Enum() *RecognitionConfig_AudioEncoding
func (RecognitionConfig_AudioEncoding) EnumDescriptor
func (RecognitionConfig_AudioEncoding) EnumDescriptor() ([]byte, []int)
Deprecated: Use RecognitionConfig_AudioEncoding.Descriptor instead.
func (RecognitionConfig_AudioEncoding) Number
func (x RecognitionConfig_AudioEncoding) Number() protoreflect.EnumNumber
func (RecognitionConfig_AudioEncoding) String
func (x RecognitionConfig_AudioEncoding) String() string
func (RecognitionConfig_AudioEncoding) Type
func (RecognitionConfig_AudioEncoding) Type() protoreflect.EnumType
RecognitionMetadata (deprecated)
type RecognitionMetadata struct {
InteractionType RecognitionMetadata_InteractionType "" /* 171 byte string literal not displayed */
IndustryNaicsCodeOfAudio uint32 "" /* 140 byte string literal not displayed */
MicrophoneDistance RecognitionMetadata_MicrophoneDistance "" /* 183 byte string literal not displayed */
OriginalMediaType RecognitionMetadata_OriginalMediaType "" /* 181 byte string literal not displayed */
RecordingDeviceType RecognitionMetadata_RecordingDeviceType "" /* 189 byte string literal not displayed */
RecordingDeviceName string `protobuf:"bytes,7,opt,name=recording_device_name,json=recordingDeviceName,proto3" json:"recording_device_name,omitempty"`
OriginalMimeType string `protobuf:"bytes,8,opt,name=original_mime_type,json=originalMimeType,proto3" json:"original_mime_type,omitempty"`
AudioTopic string `protobuf:"bytes,10,opt,name=audio_topic,json=audioTopic,proto3" json:"audio_topic,omitempty"`
}
Description of audio data to be recognized.
Deprecated: Marked as deprecated in google/cloud/speech/v1/cloud_speech.proto.
func (*RecognitionMetadata) Descriptor (deprecated)
func (*RecognitionMetadata) Descriptor() ([]byte, []int)
Deprecated: Use RecognitionMetadata.ProtoReflect.Descriptor instead.
func (*RecognitionMetadata) GetAudioTopic (deprecated)
func (x *RecognitionMetadata) GetAudioTopic() string
func (*RecognitionMetadata) GetIndustryNaicsCodeOfAudio (deprecated)
func (x *RecognitionMetadata) GetIndustryNaicsCodeOfAudio() uint32
func (*RecognitionMetadata) GetInteractionType (deprecated)
func (x *RecognitionMetadata) GetInteractionType() RecognitionMetadata_InteractionType
func (*RecognitionMetadata) GetMicrophoneDistance (deprecated)
func (x *RecognitionMetadata) GetMicrophoneDistance() RecognitionMetadata_MicrophoneDistance
func (*RecognitionMetadata) GetOriginalMediaType (deprecated)
func (x *RecognitionMetadata) GetOriginalMediaType() RecognitionMetadata_OriginalMediaType
func (*RecognitionMetadata) GetOriginalMimeType (deprecated)
func (x *RecognitionMetadata) GetOriginalMimeType() string
func (*RecognitionMetadata) GetRecordingDeviceName (deprecated)
func (x *RecognitionMetadata) GetRecordingDeviceName() string
func (*RecognitionMetadata) GetRecordingDeviceType (deprecated)
func (x *RecognitionMetadata) GetRecordingDeviceType() RecognitionMetadata_RecordingDeviceType
func (*RecognitionMetadata) ProtoMessage (deprecated)
func (*RecognitionMetadata) ProtoMessage()
func (*RecognitionMetadata) ProtoReflect (deprecated)
func (x *RecognitionMetadata) ProtoReflect() protoreflect.Message
func (*RecognitionMetadata) Reset (deprecated)
func (x *RecognitionMetadata) Reset()
func (*RecognitionMetadata) String (deprecated)
func (x *RecognitionMetadata) String() string
RecognitionMetadata_InteractionType
type RecognitionMetadata_InteractionType int32
Use case categories that the audio recognition request can be described by.
RecognitionMetadata_INTERACTION_TYPE_UNSPECIFIED, RecognitionMetadata_DISCUSSION, RecognitionMetadata_PRESENTATION, RecognitionMetadata_PHONE_CALL, RecognitionMetadata_VOICEMAIL, RecognitionMetadata_PROFESSIONALLY_PRODUCED, RecognitionMetadata_VOICE_SEARCH, RecognitionMetadata_VOICE_COMMAND, RecognitionMetadata_DICTATION
const (
// Use case is either unknown or is something other than one of the other
// values below.
RecognitionMetadata_INTERACTION_TYPE_UNSPECIFIED RecognitionMetadata_InteractionType = 0
// Multiple people in a conversation or discussion. For example in a
// meeting with two or more people actively participating. Typically
// all the primary people speaking would be in the same room (if not,
// see PHONE_CALL)
RecognitionMetadata_DISCUSSION RecognitionMetadata_InteractionType = 1
// One or more persons lecturing or presenting to others, mostly
// uninterrupted.
RecognitionMetadata_PRESENTATION RecognitionMetadata_InteractionType = 2
// A phone-call or video-conference in which two or more people, who are
// not in the same room, are actively participating.
RecognitionMetadata_PHONE_CALL RecognitionMetadata_InteractionType = 3
// A recorded message intended for another person to listen to.
RecognitionMetadata_VOICEMAIL RecognitionMetadata_InteractionType = 4
// Professionally produced audio (eg. TV Show, Podcast).
RecognitionMetadata_PROFESSIONALLY_PRODUCED RecognitionMetadata_InteractionType = 5
// Transcribe spoken questions and queries into text.
RecognitionMetadata_VOICE_SEARCH RecognitionMetadata_InteractionType = 6
// Transcribe voice commands, such as for controlling a device.
RecognitionMetadata_VOICE_COMMAND RecognitionMetadata_InteractionType = 7
// Transcribe speech to text to create a written document, such as a
// text-message, email or report.
RecognitionMetadata_DICTATION RecognitionMetadata_InteractionType = 8
)
func (RecognitionMetadata_InteractionType) Descriptor
func (RecognitionMetadata_InteractionType) Descriptor() protoreflect.EnumDescriptor
func (RecognitionMetadata_InteractionType) Enum
func (x RecognitionMetadata_InteractionType) Enum() *RecognitionMetadata_InteractionType
func (RecognitionMetadata_InteractionType) EnumDescriptor
func (RecognitionMetadata_InteractionType) EnumDescriptor() ([]byte, []int)
Deprecated: Use RecognitionMetadata_InteractionType.Descriptor instead.
func (RecognitionMetadata_InteractionType) Number
func (x RecognitionMetadata_InteractionType) Number() protoreflect.EnumNumber
func (RecognitionMetadata_InteractionType) String
func (x RecognitionMetadata_InteractionType) String() string
func (RecognitionMetadata_InteractionType) Type
func (RecognitionMetadata_InteractionType) Type() protoreflect.EnumType
RecognitionMetadata_MicrophoneDistance
type RecognitionMetadata_MicrophoneDistance int32
Enumerates the types of capture settings describing an audio file.
RecognitionMetadata_MICROPHONE_DISTANCE_UNSPECIFIED, RecognitionMetadata_NEARFIELD, RecognitionMetadata_MIDFIELD, RecognitionMetadata_FARFIELD
const (
// Audio type is not known.
RecognitionMetadata_MICROPHONE_DISTANCE_UNSPECIFIED RecognitionMetadata_MicrophoneDistance = 0
// The audio was captured from a closely placed microphone. Eg. phone,
// dictaphone, or handheld microphone. Generally if there speaker is within
// 1 meter of the microphone.
RecognitionMetadata_NEARFIELD RecognitionMetadata_MicrophoneDistance = 1
// The speaker if within 3 meters of the microphone.
RecognitionMetadata_MIDFIELD RecognitionMetadata_MicrophoneDistance = 2
// The speaker is more than 3 meters away from the microphone.
RecognitionMetadata_FARFIELD RecognitionMetadata_MicrophoneDistance = 3
)
func (RecognitionMetadata_MicrophoneDistance) Descriptor
func (RecognitionMetadata_MicrophoneDistance) Descriptor() protoreflect.EnumDescriptor
func (RecognitionMetadata_MicrophoneDistance) Enum
func (RecognitionMetadata_MicrophoneDistance) EnumDescriptor
func (RecognitionMetadata_MicrophoneDistance) EnumDescriptor() ([]byte, []int)
Deprecated: Use RecognitionMetadata_MicrophoneDistance.Descriptor instead.
func (RecognitionMetadata_MicrophoneDistance) Number
func (x RecognitionMetadata_MicrophoneDistance) Number() protoreflect.EnumNumber
func (RecognitionMetadata_MicrophoneDistance) String
func (x RecognitionMetadata_MicrophoneDistance) String() string
func (RecognitionMetadata_MicrophoneDistance) Type
func (RecognitionMetadata_MicrophoneDistance) Type() protoreflect.EnumType
RecognitionMetadata_OriginalMediaType
type RecognitionMetadata_OriginalMediaType int32
The original media the speech was recorded on.
RecognitionMetadata_ORIGINAL_MEDIA_TYPE_UNSPECIFIED, RecognitionMetadata_AUDIO, RecognitionMetadata_VIDEO
const (
// Unknown original media type.
RecognitionMetadata_ORIGINAL_MEDIA_TYPE_UNSPECIFIED RecognitionMetadata_OriginalMediaType = 0
// The speech data is an audio recording.
RecognitionMetadata_AUDIO RecognitionMetadata_OriginalMediaType = 1
// The speech data originally recorded on a video.
RecognitionMetadata_VIDEO RecognitionMetadata_OriginalMediaType = 2
)
func (RecognitionMetadata_OriginalMediaType) Descriptor
func (RecognitionMetadata_OriginalMediaType) Descriptor() protoreflect.EnumDescriptor
func (RecognitionMetadata_OriginalMediaType) Enum
func (RecognitionMetadata_OriginalMediaType) EnumDescriptor
func (RecognitionMetadata_OriginalMediaType) EnumDescriptor() ([]byte, []int)
Deprecated: Use RecognitionMetadata_OriginalMediaType.Descriptor instead.
func (RecognitionMetadata_OriginalMediaType) Number
func (x RecognitionMetadata_OriginalMediaType) Number() protoreflect.EnumNumber
func (RecognitionMetadata_OriginalMediaType) String
func (x RecognitionMetadata_OriginalMediaType) String() string
func (RecognitionMetadata_OriginalMediaType) Type
func (RecognitionMetadata_OriginalMediaType) Type() protoreflect.EnumType
RecognitionMetadata_RecordingDeviceType
type RecognitionMetadata_RecordingDeviceType int32
The type of device the speech was recorded with.
RecognitionMetadata_RECORDING_DEVICE_TYPE_UNSPECIFIED, RecognitionMetadata_SMARTPHONE, RecognitionMetadata_PC, RecognitionMetadata_PHONE_LINE, RecognitionMetadata_VEHICLE, RecognitionMetadata_OTHER_OUTDOOR_DEVICE, RecognitionMetadata_OTHER_INDOOR_DEVICE
const (
// The recording device is unknown.
RecognitionMetadata_RECORDING_DEVICE_TYPE_UNSPECIFIED RecognitionMetadata_RecordingDeviceType = 0
// Speech was recorded on a smartphone.
RecognitionMetadata_SMARTPHONE RecognitionMetadata_RecordingDeviceType = 1
// Speech was recorded using a personal computer or tablet.
RecognitionMetadata_PC RecognitionMetadata_RecordingDeviceType = 2
// Speech was recorded over a phone line.
RecognitionMetadata_PHONE_LINE RecognitionMetadata_RecordingDeviceType = 3
// Speech was recorded in a vehicle.
RecognitionMetadata_VEHICLE RecognitionMetadata_RecordingDeviceType = 4
// Speech was recorded outdoors.
RecognitionMetadata_OTHER_OUTDOOR_DEVICE RecognitionMetadata_RecordingDeviceType = 5
// Speech was recorded indoors.
RecognitionMetadata_OTHER_INDOOR_DEVICE RecognitionMetadata_RecordingDeviceType = 6
)
func (RecognitionMetadata_RecordingDeviceType) Descriptor
func (RecognitionMetadata_RecordingDeviceType) Descriptor() protoreflect.EnumDescriptor
func (RecognitionMetadata_RecordingDeviceType) Enum
func (RecognitionMetadata_RecordingDeviceType) EnumDescriptor
func (RecognitionMetadata_RecordingDeviceType) EnumDescriptor() ([]byte, []int)
Deprecated: Use RecognitionMetadata_RecordingDeviceType.Descriptor instead.
func (RecognitionMetadata_RecordingDeviceType) Number
func (x RecognitionMetadata_RecordingDeviceType) Number() protoreflect.EnumNumber
func (RecognitionMetadata_RecordingDeviceType) String
func (x RecognitionMetadata_RecordingDeviceType) String() string
func (RecognitionMetadata_RecordingDeviceType) Type
func (RecognitionMetadata_RecordingDeviceType) Type() protoreflect.EnumType
RecognizeRequest
type RecognizeRequest struct {
// Required. Provides information to the recognizer that specifies how to
// process the request.
Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config,proto3" json:"config,omitempty"`
// Required. The audio data to be recognized.
Audio *RecognitionAudio `protobuf:"bytes,2,opt,name=audio,proto3" json:"audio,omitempty"`
// contains filtered or unexported fields
}
The top-level message sent by the client for the Recognize
method.
func (*RecognizeRequest) Descriptor
func (*RecognizeRequest) Descriptor() ([]byte, []int)
Deprecated: Use RecognizeRequest.ProtoReflect.Descriptor instead.
func (*RecognizeRequest) GetAudio
func (x *RecognizeRequest) GetAudio() *RecognitionAudio
func (*RecognizeRequest) GetConfig
func (x *RecognizeRequest) GetConfig() *RecognitionConfig
func (*RecognizeRequest) ProtoMessage
func (*RecognizeRequest) ProtoMessage()
func (*RecognizeRequest) ProtoReflect
func (x *RecognizeRequest) ProtoReflect() protoreflect.Message
func (*RecognizeRequest) Reset
func (x *RecognizeRequest) Reset()
func (*RecognizeRequest) String
func (x *RecognizeRequest) String() string
RecognizeResponse
type RecognizeResponse struct {
// Sequential list of transcription results corresponding to
// sequential portions of audio.
Results []*SpeechRecognitionResult `protobuf:"bytes,2,rep,name=results,proto3" json:"results,omitempty"`
// When available, billed audio seconds for the corresponding request.
TotalBilledTime *durationpb.Duration `protobuf:"bytes,3,opt,name=total_billed_time,json=totalBilledTime,proto3" json:"total_billed_time,omitempty"`
// Provides information on adaptation behavior in response
SpeechAdaptationInfo *SpeechAdaptationInfo `protobuf:"bytes,7,opt,name=speech_adaptation_info,json=speechAdaptationInfo,proto3" json:"speech_adaptation_info,omitempty"`
// The ID associated with the request. This is a unique ID specific only to
// the given request.
RequestId int64 `protobuf:"varint,8,opt,name=request_id,json=requestId,proto3" json:"request_id,omitempty"`
// contains filtered or unexported fields
}
The only message returned to the client by the Recognize
method. It
contains the result as zero or more sequential SpeechRecognitionResult
messages.
func (*RecognizeResponse) Descriptor
func (*RecognizeResponse) Descriptor() ([]byte, []int)
Deprecated: Use RecognizeResponse.ProtoReflect.Descriptor instead.
func (*RecognizeResponse) GetRequestId
func (x *RecognizeResponse) GetRequestId() int64
func (*RecognizeResponse) GetResults
func (x *RecognizeResponse) GetResults() []*SpeechRecognitionResult
func (*RecognizeResponse) GetSpeechAdaptationInfo
func (x *RecognizeResponse) GetSpeechAdaptationInfo() *SpeechAdaptationInfo
func (*RecognizeResponse) GetTotalBilledTime
func (x *RecognizeResponse) GetTotalBilledTime() *durationpb.Duration
func (*RecognizeResponse) ProtoMessage
func (*RecognizeResponse) ProtoMessage()
func (*RecognizeResponse) ProtoReflect
func (x *RecognizeResponse) ProtoReflect() protoreflect.Message
func (*RecognizeResponse) Reset
func (x *RecognizeResponse) Reset()
func (*RecognizeResponse) String
func (x *RecognizeResponse) String() string
SpeakerDiarizationConfig
type SpeakerDiarizationConfig struct {
EnableSpeakerDiarization bool "" /* 136 byte string literal not displayed */
MinSpeakerCount int32 `protobuf:"varint,2,opt,name=min_speaker_count,json=minSpeakerCount,proto3" json:"min_speaker_count,omitempty"`
MaxSpeakerCount int32 `protobuf:"varint,3,opt,name=max_speaker_count,json=maxSpeakerCount,proto3" json:"max_speaker_count,omitempty"`
SpeakerTag int32 `protobuf:"varint,5,opt,name=speaker_tag,json=speakerTag,proto3" json:"speaker_tag,omitempty"`
}
Config to enable speaker diarization.
func (*SpeakerDiarizationConfig) Descriptor
func (*SpeakerDiarizationConfig) Descriptor() ([]byte, []int)
Deprecated: Use SpeakerDiarizationConfig.ProtoReflect.Descriptor instead.
func (*SpeakerDiarizationConfig) GetEnableSpeakerDiarization
func (x *SpeakerDiarizationConfig) GetEnableSpeakerDiarization() bool
func (*SpeakerDiarizationConfig) GetMaxSpeakerCount
func (x *SpeakerDiarizationConfig) GetMaxSpeakerCount() int32
func (*SpeakerDiarizationConfig) GetMinSpeakerCount
func (x *SpeakerDiarizationConfig) GetMinSpeakerCount() int32
func (*SpeakerDiarizationConfig) GetSpeakerTag
func (x *SpeakerDiarizationConfig) GetSpeakerTag() int32
Deprecated: Marked as deprecated in google/cloud/speech/v1/cloud_speech.proto.
func (*SpeakerDiarizationConfig) ProtoMessage
func (*SpeakerDiarizationConfig) ProtoMessage()
func (*SpeakerDiarizationConfig) ProtoReflect
func (x *SpeakerDiarizationConfig) ProtoReflect() protoreflect.Message
func (*SpeakerDiarizationConfig) Reset
func (x *SpeakerDiarizationConfig) Reset()
func (*SpeakerDiarizationConfig) String
func (x *SpeakerDiarizationConfig) String() string
SpeechAdaptation
type SpeechAdaptation struct {
// A collection of phrase sets. To specify the hints inline, leave the
// phrase set's `name` blank and fill in the rest of its fields. Any
// phrase set can use any custom class.
PhraseSets []*PhraseSet `protobuf:"bytes,1,rep,name=phrase_sets,json=phraseSets,proto3" json:"phrase_sets,omitempty"`
// A collection of phrase set resource names to use.
PhraseSetReferences []string `protobuf:"bytes,2,rep,name=phrase_set_references,json=phraseSetReferences,proto3" json:"phrase_set_references,omitempty"`
// A collection of custom classes. To specify the classes inline, leave the
// class' `name` blank and fill in the rest of its fields, giving it a unique
// `custom_class_id`. Refer to the inline defined class in phrase hints by its
// `custom_class_id`.
CustomClasses []*CustomClass `protobuf:"bytes,3,rep,name=custom_classes,json=customClasses,proto3" json:"custom_classes,omitempty"`
// Augmented Backus-Naur form (ABNF) is a standardized grammar notation
// comprised by a set of derivation rules.
// See specifications: https://www.w3.org/TR/speech-grammar
AbnfGrammar *SpeechAdaptation_ABNFGrammar `protobuf:"bytes,4,opt,name=abnf_grammar,json=abnfGrammar,proto3" json:"abnf_grammar,omitempty"`
// contains filtered or unexported fields
}
Speech adaptation configuration.
func (*SpeechAdaptation) Descriptor
func (*SpeechAdaptation) Descriptor() ([]byte, []int)
Deprecated: Use SpeechAdaptation.ProtoReflect.Descriptor instead.
func (*SpeechAdaptation) GetAbnfGrammar
func (x *SpeechAdaptation) GetAbnfGrammar() *SpeechAdaptation_ABNFGrammar
func (*SpeechAdaptation) GetCustomClasses
func (x *SpeechAdaptation) GetCustomClasses() []*CustomClass
func (*SpeechAdaptation) GetPhraseSetReferences
func (x *SpeechAdaptation) GetPhraseSetReferences() []string
func (*SpeechAdaptation) GetPhraseSets
func (x *SpeechAdaptation) GetPhraseSets() []*PhraseSet
func (*SpeechAdaptation) ProtoMessage
func (*SpeechAdaptation) ProtoMessage()
func (*SpeechAdaptation) ProtoReflect
func (x *SpeechAdaptation) ProtoReflect() protoreflect.Message
func (*SpeechAdaptation) Reset
func (x *SpeechAdaptation) Reset()
func (*SpeechAdaptation) String
func (x *SpeechAdaptation) String() string
SpeechAdaptationInfo
type SpeechAdaptationInfo struct {
// Whether there was a timeout when applying speech adaptation. If true,
// adaptation had no effect in the response transcript.
AdaptationTimeout bool `protobuf:"varint,1,opt,name=adaptation_timeout,json=adaptationTimeout,proto3" json:"adaptation_timeout,omitempty"`
// If set, returns a message specifying which part of the speech adaptation
// request timed out.
TimeoutMessage string `protobuf:"bytes,4,opt,name=timeout_message,json=timeoutMessage,proto3" json:"timeout_message,omitempty"`
// contains filtered or unexported fields
}
Information on speech adaptation use in results
func (*SpeechAdaptationInfo) Descriptor
func (*SpeechAdaptationInfo) Descriptor() ([]byte, []int)
Deprecated: Use SpeechAdaptationInfo.ProtoReflect.Descriptor instead.
func (*SpeechAdaptationInfo) GetAdaptationTimeout
func (x *SpeechAdaptationInfo) GetAdaptationTimeout() bool
func (*SpeechAdaptationInfo) GetTimeoutMessage
func (x *SpeechAdaptationInfo) GetTimeoutMessage() string
func (*SpeechAdaptationInfo) ProtoMessage
func (*SpeechAdaptationInfo) ProtoMessage()
func (*SpeechAdaptationInfo) ProtoReflect
func (x *SpeechAdaptationInfo) ProtoReflect() protoreflect.Message
func (*SpeechAdaptationInfo) Reset
func (x *SpeechAdaptationInfo) Reset()
func (*SpeechAdaptationInfo) String
func (x *SpeechAdaptationInfo) String() string
SpeechAdaptation_ABNFGrammar
type SpeechAdaptation_ABNFGrammar struct {
// All declarations and rules of an ABNF grammar broken up into multiple
// strings that will end up concatenated.
AbnfStrings []string `protobuf:"bytes,1,rep,name=abnf_strings,json=abnfStrings,proto3" json:"abnf_strings,omitempty"`
// contains filtered or unexported fields
}
func (*SpeechAdaptation_ABNFGrammar) Descriptor
func (*SpeechAdaptation_ABNFGrammar) Descriptor() ([]byte, []int)
Deprecated: Use SpeechAdaptation_ABNFGrammar.ProtoReflect.Descriptor instead.
func (*SpeechAdaptation_ABNFGrammar) GetAbnfStrings
func (x *SpeechAdaptation_ABNFGrammar) GetAbnfStrings() []string
func (*SpeechAdaptation_ABNFGrammar) ProtoMessage
func (*SpeechAdaptation_ABNFGrammar) ProtoMessage()
func (*SpeechAdaptation_ABNFGrammar) ProtoReflect
func (x *SpeechAdaptation_ABNFGrammar) ProtoReflect() protoreflect.Message
func (*SpeechAdaptation_ABNFGrammar) Reset
func (x *SpeechAdaptation_ABNFGrammar) Reset()
func (*SpeechAdaptation_ABNFGrammar) String
func (x *SpeechAdaptation_ABNFGrammar) String() string
SpeechClient
type SpeechClient interface {
// Performs synchronous speech recognition: receive results after all audio
// has been sent and processed.
Recognize(ctx context.Context, in *RecognizeRequest, opts ...grpc.CallOption) (*RecognizeResponse, error)
// Performs asynchronous speech recognition: receive results via the
// google.longrunning.Operations interface. Returns either an
// `Operation.error` or an `Operation.response` which contains
// a `LongRunningRecognizeResponse` message.
// For more information on asynchronous speech recognition, see the
// [how-to](https://cloud.google.com/speech-to-text/docs/async-recognize).
LongRunningRecognize(ctx context.Context, in *LongRunningRecognizeRequest, opts ...grpc.CallOption) (*longrunningpb.Operation, error)
// Performs bidirectional streaming speech recognition: receive results while
// sending audio. This method is only available via the gRPC API (not REST).
StreamingRecognize(ctx context.Context, opts ...grpc.CallOption) (Speech_StreamingRecognizeClient, error)
}
SpeechClient is the client API for Speech service.
For semantics around ctx use and closing/ending streaming RPCs, please refer to https://godoc.org/google.golang.org/grpc#ClientConn.NewStream.
func NewSpeechClient
func NewSpeechClient(cc grpc.ClientConnInterface) SpeechClient
SpeechContext
type SpeechContext struct {
// A list of strings containing words and phrases "hints" so that
// the speech recognition is more likely to recognize them. This can be used
// to improve the accuracy for specific words and phrases, for example, if
// specific commands are typically spoken by the user. This can also be used
// to add additional words to the vocabulary of the recognizer. See
// [usage limits](https://cloud.google.com/speech-to-text/quotas#content).
//
// List items can also be set to classes for groups of words that represent
// common concepts that occur in natural language. For example, rather than
// providing phrase hints for every month of the year, using the $MONTH class
// improves the likelihood of correctly transcribing audio that includes
// months.
Phrases []string `protobuf:"bytes,1,rep,name=phrases,proto3" json:"phrases,omitempty"`
// Hint Boost. Positive value will increase the probability that a specific
// phrase will be recognized over other similar sounding phrases. The higher
// the boost, the higher the chance of false positive recognition as well.
// Negative boost values would correspond to anti-biasing. Anti-biasing is not
// enabled, so negative boost will simply be ignored. Though `boost` can
// accept a wide range of positive values, most use cases are best served with
// values between 0 and 20. We recommend using a binary search approach to
// finding the optimal value for your use case.
Boost float32 `protobuf:"fixed32,4,opt,name=boost,proto3" json:"boost,omitempty"`
// contains filtered or unexported fields
}
Provides "hints" to the speech recognizer to favor specific words and phrases in the results.
func (*SpeechContext) Descriptor
func (*SpeechContext) Descriptor() ([]byte, []int)
Deprecated: Use SpeechContext.ProtoReflect.Descriptor instead.
func (*SpeechContext) GetBoost
func (x *SpeechContext) GetBoost() float32
func (*SpeechContext) GetPhrases
func (x *SpeechContext) GetPhrases() []string
func (*SpeechContext) ProtoMessage
func (*SpeechContext) ProtoMessage()
func (*SpeechContext) ProtoReflect
func (x *SpeechContext) ProtoReflect() protoreflect.Message
func (*SpeechContext) Reset
func (x *SpeechContext) Reset()
func (*SpeechContext) String
func (x *SpeechContext) String() string
SpeechRecognitionAlternative
type SpeechRecognitionAlternative struct {
// Transcript text representing the words that the user spoke.
// In languages that use spaces to separate words, the transcript might have a
// leading space if it isn't the first result. You can concatenate each result
// to obtain the full transcript without using a separator.
Transcript string `protobuf:"bytes,1,opt,name=transcript,proto3" json:"transcript,omitempty"`
// The confidence estimate between 0.0 and 1.0. A higher number
// indicates an estimated greater likelihood that the recognized words are
// correct. This field is set only for the top alternative of a non-streaming
// result or, of a streaming result where `is_final=true`.
// This field is not guaranteed to be accurate and users should not rely on it
// to be always provided.
// The default of 0.0 is a sentinel value indicating `confidence` was not set.
Confidence float32 `protobuf:"fixed32,2,opt,name=confidence,proto3" json:"confidence,omitempty"`
// A list of word-specific information for each recognized word.
// Note: When `enable_speaker_diarization` is true, you will see all the words
// from the beginning of the audio.
Words []*WordInfo `protobuf:"bytes,3,rep,name=words,proto3" json:"words,omitempty"`
// contains filtered or unexported fields
}
Alternative hypotheses (a.k.a. n-best list).
func (*SpeechRecognitionAlternative) Descriptor
func (*SpeechRecognitionAlternative) Descriptor() ([]byte, []int)
Deprecated: Use SpeechRecognitionAlternative.ProtoReflect.Descriptor instead.
func (*SpeechRecognitionAlternative) GetConfidence
func (x *SpeechRecognitionAlternative) GetConfidence() float32
func (*SpeechRecognitionAlternative) GetTranscript
func (x *SpeechRecognitionAlternative) GetTranscript() string
func (*SpeechRecognitionAlternative) GetWords
func (x *SpeechRecognitionAlternative) GetWords() []*WordInfo
func (*SpeechRecognitionAlternative) ProtoMessage
func (*SpeechRecognitionAlternative) ProtoMessage()
func (*SpeechRecognitionAlternative) ProtoReflect
func (x *SpeechRecognitionAlternative) ProtoReflect() protoreflect.Message
func (*SpeechRecognitionAlternative) Reset
func (x *SpeechRecognitionAlternative) Reset()
func (*SpeechRecognitionAlternative) String
func (x *SpeechRecognitionAlternative) String() string
SpeechRecognitionResult
type SpeechRecognitionResult struct {
// May contain one or more recognition hypotheses (up to the
// maximum specified in `max_alternatives`).
// These alternatives are ordered in terms of accuracy, with the top (first)
// alternative being the most probable, as ranked by the recognizer.
Alternatives []*SpeechRecognitionAlternative `protobuf:"bytes,1,rep,name=alternatives,proto3" json:"alternatives,omitempty"`
// For multi-channel audio, this is the channel number corresponding to the
// recognized result for the audio from that channel.
// For audio_channel_count = N, its output values can range from '1' to 'N'.
ChannelTag int32 `protobuf:"varint,2,opt,name=channel_tag,json=channelTag,proto3" json:"channel_tag,omitempty"`
// Time offset of the end of this result relative to the
// beginning of the audio.
ResultEndTime *durationpb.Duration `protobuf:"bytes,4,opt,name=result_end_time,json=resultEndTime,proto3" json:"result_end_time,omitempty"`
// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
// language tag of the language in this result. This language code was
// detected to have the most likelihood of being spoken in the audio.
LanguageCode string `protobuf:"bytes,5,opt,name=language_code,json=languageCode,proto3" json:"language_code,omitempty"`
// contains filtered or unexported fields
}
A speech recognition result corresponding to a portion of the audio.
func (*SpeechRecognitionResult) Descriptor
func (*SpeechRecognitionResult) Descriptor() ([]byte, []int)
Deprecated: Use SpeechRecognitionResult.ProtoReflect.Descriptor instead.
func (*SpeechRecognitionResult) GetAlternatives
func (x *SpeechRecognitionResult) GetAlternatives() []*SpeechRecognitionAlternative
func (*SpeechRecognitionResult) GetChannelTag
func (x *SpeechRecognitionResult) GetChannelTag() int32
func (*SpeechRecognitionResult) GetLanguageCode
func (x *SpeechRecognitionResult) GetLanguageCode() string
func (*SpeechRecognitionResult) GetResultEndTime
func (x *SpeechRecognitionResult) GetResultEndTime() *durationpb.Duration
func (*SpeechRecognitionResult) ProtoMessage
func (*SpeechRecognitionResult) ProtoMessage()
func (*SpeechRecognitionResult) ProtoReflect
func (x *SpeechRecognitionResult) ProtoReflect() protoreflect.Message
func (*SpeechRecognitionResult) Reset
func (x *SpeechRecognitionResult) Reset()
func (*SpeechRecognitionResult) String
func (x *SpeechRecognitionResult) String() string
SpeechServer
type SpeechServer interface {
// Performs synchronous speech recognition: receive results after all audio
// has been sent and processed.
Recognize(context.Context, *RecognizeRequest) (*RecognizeResponse, error)
// Performs asynchronous speech recognition: receive results via the
// google.longrunning.Operations interface. Returns either an
// `Operation.error` or an `Operation.response` which contains
// a `LongRunningRecognizeResponse` message.
// For more information on asynchronous speech recognition, see the
// [how-to](https://cloud.google.com/speech-to-text/docs/async-recognize).
LongRunningRecognize(context.Context, *LongRunningRecognizeRequest) (*longrunningpb.Operation, error)
// Performs bidirectional streaming speech recognition: receive results while
// sending audio. This method is only available via the gRPC API (not REST).
StreamingRecognize(Speech_StreamingRecognizeServer) error
}
SpeechServer is the server API for Speech service.
Speech_StreamingRecognizeClient
type Speech_StreamingRecognizeClient interface {
Send(*StreamingRecognizeRequest) error
Recv() (*StreamingRecognizeResponse, error)
grpc.ClientStream
}
Speech_StreamingRecognizeServer
type Speech_StreamingRecognizeServer interface {
Send(*StreamingRecognizeResponse) error
Recv() (*StreamingRecognizeRequest, error)
grpc.ServerStream
}
StreamingRecognitionConfig
type StreamingRecognitionConfig struct {
Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config,proto3" json:"config,omitempty"`
SingleUtterance bool `protobuf:"varint,2,opt,name=single_utterance,json=singleUtterance,proto3" json:"single_utterance,omitempty"`
InterimResults bool `protobuf:"varint,3,opt,name=interim_results,json=interimResults,proto3" json:"interim_results,omitempty"`
EnableVoiceActivityEvents bool "" /* 141 byte string literal not displayed */
VoiceActivityTimeout *StreamingRecognitionConfig_VoiceActivityTimeout `protobuf:"bytes,6,opt,name=voice_activity_timeout,json=voiceActivityTimeout,proto3" json:"voice_activity_timeout,omitempty"`
}
Provides information to the recognizer that specifies how to process the request.
func (*StreamingRecognitionConfig) Descriptor
func (*StreamingRecognitionConfig) Descriptor() ([]byte, []int)
Deprecated: Use StreamingRecognitionConfig.ProtoReflect.Descriptor instead.
func (*StreamingRecognitionConfig) GetConfig
func (x *StreamingRecognitionConfig) GetConfig() *RecognitionConfig
func (*StreamingRecognitionConfig) GetEnableVoiceActivityEvents
func (x *StreamingRecognitionConfig) GetEnableVoiceActivityEvents() bool
func (*StreamingRecognitionConfig) GetInterimResults
func (x *StreamingRecognitionConfig) GetInterimResults() bool
func (*StreamingRecognitionConfig) GetSingleUtterance
func (x *StreamingRecognitionConfig) GetSingleUtterance() bool
func (*StreamingRecognitionConfig) GetVoiceActivityTimeout
func (x *StreamingRecognitionConfig) GetVoiceActivityTimeout() *StreamingRecognitionConfig_VoiceActivityTimeout
func (*StreamingRecognitionConfig) ProtoMessage
func (*StreamingRecognitionConfig) ProtoMessage()
func (*StreamingRecognitionConfig) ProtoReflect
func (x *StreamingRecognitionConfig) ProtoReflect() protoreflect.Message
func (*StreamingRecognitionConfig) Reset
func (x *StreamingRecognitionConfig) Reset()
func (*StreamingRecognitionConfig) String
func (x *StreamingRecognitionConfig) String() string
StreamingRecognitionConfig_VoiceActivityTimeout
type StreamingRecognitionConfig_VoiceActivityTimeout struct {
// Duration to timeout the stream if no speech begins.
SpeechStartTimeout *durationpb.Duration `protobuf:"bytes,1,opt,name=speech_start_timeout,json=speechStartTimeout,proto3" json:"speech_start_timeout,omitempty"`
// Duration to timeout the stream after speech ends.
SpeechEndTimeout *durationpb.Duration `protobuf:"bytes,2,opt,name=speech_end_timeout,json=speechEndTimeout,proto3" json:"speech_end_timeout,omitempty"`
// contains filtered or unexported fields
}
Events that a timeout can be set on for voice activity.
func (*StreamingRecognitionConfig_VoiceActivityTimeout) Descriptor
func (*StreamingRecognitionConfig_VoiceActivityTimeout) Descriptor() ([]byte, []int)
Deprecated: Use StreamingRecognitionConfig_VoiceActivityTimeout.ProtoReflect.Descriptor instead.
func (*StreamingRecognitionConfig_VoiceActivityTimeout) GetSpeechEndTimeout
func (x *StreamingRecognitionConfig_VoiceActivityTimeout) GetSpeechEndTimeout() *durationpb.Duration
func (*StreamingRecognitionConfig_VoiceActivityTimeout) GetSpeechStartTimeout
func (x *StreamingRecognitionConfig_VoiceActivityTimeout) GetSpeechStartTimeout() *durationpb.Duration
func (*StreamingRecognitionConfig_VoiceActivityTimeout) ProtoMessage
func (*StreamingRecognitionConfig_VoiceActivityTimeout) ProtoMessage()
func (*StreamingRecognitionConfig_VoiceActivityTimeout) ProtoReflect
func (x *StreamingRecognitionConfig_VoiceActivityTimeout) ProtoReflect() protoreflect.Message
func (*StreamingRecognitionConfig_VoiceActivityTimeout) Reset
func (x *StreamingRecognitionConfig_VoiceActivityTimeout) Reset()
func (*StreamingRecognitionConfig_VoiceActivityTimeout) String
func (x *StreamingRecognitionConfig_VoiceActivityTimeout) String() string
StreamingRecognitionResult
type StreamingRecognitionResult struct {
// May contain one or more recognition hypotheses (up to the
// maximum specified in `max_alternatives`).
// These alternatives are ordered in terms of accuracy, with the top (first)
// alternative being the most probable, as ranked by the recognizer.
Alternatives []*SpeechRecognitionAlternative `protobuf:"bytes,1,rep,name=alternatives,proto3" json:"alternatives,omitempty"`
// If `false`, this `StreamingRecognitionResult` represents an
// interim result that may change. If `true`, this is the final time the
// speech service will return this particular `StreamingRecognitionResult`,
// the recognizer will not return any further hypotheses for this portion of
// the transcript and corresponding audio.
IsFinal bool `protobuf:"varint,2,opt,name=is_final,json=isFinal,proto3" json:"is_final,omitempty"`
// An estimate of the likelihood that the recognizer will not
// change its guess about this interim result. Values range from 0.0
// (completely unstable) to 1.0 (completely stable).
// This field is only provided for interim results (`is_final=false`).
// The default of 0.0 is a sentinel value indicating `stability` was not set.
Stability float32 `protobuf:"fixed32,3,opt,name=stability,proto3" json:"stability,omitempty"`
// Time offset of the end of this result relative to the
// beginning of the audio.
ResultEndTime *durationpb.Duration `protobuf:"bytes,4,opt,name=result_end_time,json=resultEndTime,proto3" json:"result_end_time,omitempty"`
// For multi-channel audio, this is the channel number corresponding to the
// recognized result for the audio from that channel.
// For audio_channel_count = N, its output values can range from '1' to 'N'.
ChannelTag int32 `protobuf:"varint,5,opt,name=channel_tag,json=channelTag,proto3" json:"channel_tag,omitempty"`
// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
// language tag of the language in this result. This language code was
// detected to have the most likelihood of being spoken in the audio.
LanguageCode string `protobuf:"bytes,6,opt,name=language_code,json=languageCode,proto3" json:"language_code,omitempty"`
// contains filtered or unexported fields
}
A streaming speech recognition result corresponding to a portion of the audio that is currently being processed.
func (*StreamingRecognitionResult) Descriptor
func (*StreamingRecognitionResult) Descriptor() ([]byte, []int)
Deprecated: Use StreamingRecognitionResult.ProtoReflect.Descriptor instead.
func (*StreamingRecognitionResult) GetAlternatives
func (x *StreamingRecognitionResult) GetAlternatives() []*SpeechRecognitionAlternative
func (*StreamingRecognitionResult) GetChannelTag
func (x *StreamingRecognitionResult) GetChannelTag() int32
func (*StreamingRecognitionResult) GetIsFinal
func (x *StreamingRecognitionResult) GetIsFinal() bool
func (*StreamingRecognitionResult) GetLanguageCode
func (x *StreamingRecognitionResult) GetLanguageCode() string
func (*StreamingRecognitionResult) GetResultEndTime
func (x *StreamingRecognitionResult) GetResultEndTime() *durationpb.Duration
func (*StreamingRecognitionResult) GetStability
func (x *StreamingRecognitionResult) GetStability() float32
func (*StreamingRecognitionResult) ProtoMessage
func (*StreamingRecognitionResult) ProtoMessage()
func (*StreamingRecognitionResult) ProtoReflect
func (x *StreamingRecognitionResult) ProtoReflect() protoreflect.Message
func (*StreamingRecognitionResult) Reset
func (x *StreamingRecognitionResult) Reset()
func (*StreamingRecognitionResult) String
func (x *StreamingRecognitionResult) String() string
StreamingRecognizeRequest
type StreamingRecognizeRequest struct {
// The streaming request, which is either a streaming config or audio content.
//
// Types that are assignable to StreamingRequest:
// *StreamingRecognizeRequest_StreamingConfig
// *StreamingRecognizeRequest_AudioContent
StreamingRequest isStreamingRecognizeRequest_StreamingRequest `protobuf_oneof:"streaming_request"`
// contains filtered or unexported fields
}
The top-level message sent by the client for the StreamingRecognize
method.
Multiple StreamingRecognizeRequest
messages are sent. The first message
must contain a streaming_config
message and must not contain
audio_content
. All subsequent messages must contain audio_content
and
must not contain a streaming_config
message.
func (*StreamingRecognizeRequest) Descriptor
func (*StreamingRecognizeRequest) Descriptor() ([]byte, []int)
Deprecated: Use StreamingRecognizeRequest.ProtoReflect.Descriptor instead.
func (*StreamingRecognizeRequest) GetAudioContent
func (x *StreamingRecognizeRequest) GetAudioContent() []byte
func (*StreamingRecognizeRequest) GetStreamingConfig
func (x *StreamingRecognizeRequest) GetStreamingConfig() *StreamingRecognitionConfig
func (*StreamingRecognizeRequest) GetStreamingRequest
func (m *StreamingRecognizeRequest) GetStreamingRequest() isStreamingRecognizeRequest_StreamingRequest
func (*StreamingRecognizeRequest) ProtoMessage
func (*StreamingRecognizeRequest) ProtoMessage()
func (*StreamingRecognizeRequest) ProtoReflect
func (x *StreamingRecognizeRequest) ProtoReflect() protoreflect.Message
func (*StreamingRecognizeRequest) Reset
func (x *StreamingRecognizeRequest) Reset()
func (*StreamingRecognizeRequest) String
func (x *StreamingRecognizeRequest) String() string
StreamingRecognizeRequest_AudioContent
type StreamingRecognizeRequest_AudioContent struct {
// The audio data to be recognized. Sequential chunks of audio data are sent
// in sequential `StreamingRecognizeRequest` messages. The first
// `StreamingRecognizeRequest` message must not contain `audio_content` data
// and all subsequent `StreamingRecognizeRequest` messages must contain
// `audio_content` data. The audio bytes must be encoded as specified in
// `RecognitionConfig`. Note: as with all bytes fields, proto buffers use a
// pure binary representation (not base64). See
// [content limits](https://cloud.google.com/speech-to-text/quotas#content).
AudioContent []byte `protobuf:"bytes,2,opt,name=audio_content,json=audioContent,proto3,oneof"`
}
StreamingRecognizeRequest_StreamingConfig
type StreamingRecognizeRequest_StreamingConfig struct {
// Provides information to the recognizer that specifies how to process the
// request. The first `StreamingRecognizeRequest` message must contain a
// `streaming_config` message.
StreamingConfig *StreamingRecognitionConfig `protobuf:"bytes,1,opt,name=streaming_config,json=streamingConfig,proto3,oneof"`
}
StreamingRecognizeResponse
type StreamingRecognizeResponse struct {
Error *status.Status `protobuf:"bytes,1,opt,name=error,proto3" json:"error,omitempty"`
Results []*StreamingRecognitionResult `protobuf:"bytes,2,rep,name=results,proto3" json:"results,omitempty"`
SpeechEventType StreamingRecognizeResponse_SpeechEventType "" /* 180 byte string literal not displayed */
SpeechEventTime *durationpb.Duration `protobuf:"bytes,8,opt,name=speech_event_time,json=speechEventTime,proto3" json:"speech_event_time,omitempty"`
TotalBilledTime *durationpb.Duration `protobuf:"bytes,5,opt,name=total_billed_time,json=totalBilledTime,proto3" json:"total_billed_time,omitempty"`
SpeechAdaptationInfo *SpeechAdaptationInfo `protobuf:"bytes,9,opt,name=speech_adaptation_info,json=speechAdaptationInfo,proto3" json:"speech_adaptation_info,omitempty"`
RequestId int64 `protobuf:"varint,10,opt,name=request_id,json=requestId,proto3" json:"request_id,omitempty"`
}
StreamingRecognizeResponse
is the only message returned to the client by
StreamingRecognize
. A series of zero or more StreamingRecognizeResponse
messages are streamed back to the client. If there is no recognizable
audio, and single_utterance
is set to false, then no messages are streamed
back to the client.
Here's an example of a series of StreamingRecognizeResponse
s that might be
returned while processing audio:
results { alternatives { transcript: "tube" } stability: 0.01 }
results { alternatives { transcript: "to be a" } stability: 0.01 }
results { alternatives { transcript: "to be" } stability: 0.9 } results { alternatives { transcript: " or not to be" } stability: 0.01 }
results { alternatives { transcript: "to be or not to be" confidence: 0.92 } alternatives { transcript: "to bee or not to bee" } is_final: true }
results { alternatives { transcript: " that's" } stability: 0.01 }
results { alternatives { transcript: " that is" } stability: 0.9 } results { alternatives { transcript: " the question" } stability: 0.01 }
results { alternatives { transcript: " that is the question" confidence: 0.98 } alternatives { transcript: " that was the question" } is_final: true }
Notes:
Only two of the above responses #4 and #7 contain final results; they are indicated by
is_final: true
. Concatenating these together generates the full transcript: "to be or not to be that is the question".The others contain interim
results
. #3 and #6 contain two interimresults
: the first portion has a high stability and is less likely to change; the second portion has a low stability and is very likely to change. A UI designer might choose to show only high stabilityresults
.The specific
stability
andconfidence
values shown above are only for illustrative purposes. Actual values may vary.In each response, only one of these fields will be set:
error
,speech_event_type
, or one or more (repeated)results
.
func (*StreamingRecognizeResponse) Descriptor
func (*StreamingRecognizeResponse) Descriptor() ([]byte, []int)
Deprecated: Use StreamingRecognizeResponse.ProtoReflect.Descriptor instead.
func (*StreamingRecognizeResponse) GetError
func (x *StreamingRecognizeResponse) GetError() *status.Status
func (*StreamingRecognizeResponse) GetRequestId
func (x *StreamingRecognizeResponse) GetRequestId() int64
func (*StreamingRecognizeResponse) GetResults
func (x *StreamingRecognizeResponse) GetResults() []*StreamingRecognitionResult
func (*StreamingRecognizeResponse) GetSpeechAdaptationInfo
func (x *StreamingRecognizeResponse) GetSpeechAdaptationInfo() *SpeechAdaptationInfo
func (*StreamingRecognizeResponse) GetSpeechEventTime
func (x *StreamingRecognizeResponse) GetSpeechEventTime() *durationpb.Duration
func (*StreamingRecognizeResponse) GetSpeechEventType
func (x *StreamingRecognizeResponse) GetSpeechEventType() StreamingRecognizeResponse_SpeechEventType
func (*StreamingRecognizeResponse) GetTotalBilledTime
func (x *StreamingRecognizeResponse) GetTotalBilledTime() *durationpb.Duration
func (*StreamingRecognizeResponse) ProtoMessage
func (*StreamingRecognizeResponse) ProtoMessage()
func (*StreamingRecognizeResponse) ProtoReflect
func (x *StreamingRecognizeResponse) ProtoReflect() protoreflect.Message
func (*StreamingRecognizeResponse) Reset
func (x *StreamingRecognizeResponse) Reset()
func (*StreamingRecognizeResponse) String
func (x *StreamingRecognizeResponse) String() string
StreamingRecognizeResponse_SpeechEventType
type StreamingRecognizeResponse_SpeechEventType int32
Indicates the type of speech event.
StreamingRecognizeResponse_SPEECH_EVENT_UNSPECIFIED, StreamingRecognizeResponse_END_OF_SINGLE_UTTERANCE, StreamingRecognizeResponse_SPEECH_ACTIVITY_BEGIN, StreamingRecognizeResponse_SPEECH_ACTIVITY_END, StreamingRecognizeResponse_SPEECH_ACTIVITY_TIMEOUT
const (
// No speech event specified.
StreamingRecognizeResponse_SPEECH_EVENT_UNSPECIFIED StreamingRecognizeResponse_SpeechEventType = 0
// This event indicates that the server has detected the end of the user's
// speech utterance and expects no additional speech. Therefore, the server
// will not process additional audio (although it may subsequently return
// additional results). The client should stop sending additional audio
// data, half-close the gRPC connection, and wait for any additional results
// until the server closes the gRPC connection. This event is only sent if
// `single_utterance` was set to `true`, and is not used otherwise.
StreamingRecognizeResponse_END_OF_SINGLE_UTTERANCE StreamingRecognizeResponse_SpeechEventType = 1
// This event indicates that the server has detected the beginning of human
// voice activity in the stream. This event can be returned multiple times
// if speech starts and stops repeatedly throughout the stream. This event
// is only sent if `voice_activity_events` is set to true.
StreamingRecognizeResponse_SPEECH_ACTIVITY_BEGIN StreamingRecognizeResponse_SpeechEventType = 2
// This event indicates that the server has detected the end of human voice
// activity in the stream. This event can be returned multiple times if
// speech starts and stops repeatedly throughout the stream. This event is
// only sent if `voice_activity_events` is set to true.
StreamingRecognizeResponse_SPEECH_ACTIVITY_END StreamingRecognizeResponse_SpeechEventType = 3
// This event indicates that the user-set timeout for speech activity begin
// or end has exceeded. Upon receiving this event, the client is expected to
// send a half close. Further audio will not be processed.
StreamingRecognizeResponse_SPEECH_ACTIVITY_TIMEOUT StreamingRecognizeResponse_SpeechEventType = 4
)
func (StreamingRecognizeResponse_SpeechEventType) Descriptor
func (StreamingRecognizeResponse_SpeechEventType) Descriptor() protoreflect.EnumDescriptor
func (StreamingRecognizeResponse_SpeechEventType) Enum
func (x StreamingRecognizeResponse_SpeechEventType) Enum() *StreamingRecognizeResponse_SpeechEventType
func (StreamingRecognizeResponse_SpeechEventType) EnumDescriptor
func (StreamingRecognizeResponse_SpeechEventType) EnumDescriptor() ([]byte, []int)
Deprecated: Use StreamingRecognizeResponse_SpeechEventType.Descriptor instead.
func (StreamingRecognizeResponse_SpeechEventType) Number
func (x StreamingRecognizeResponse_SpeechEventType) Number() protoreflect.EnumNumber
func (StreamingRecognizeResponse_SpeechEventType) String
func (x StreamingRecognizeResponse_SpeechEventType) String() string
func (StreamingRecognizeResponse_SpeechEventType) Type
func (StreamingRecognizeResponse_SpeechEventType) Type() protoreflect.EnumType
TranscriptOutputConfig
type TranscriptOutputConfig struct {
// Types that are assignable to OutputType:
// *TranscriptOutputConfig_GcsUri
OutputType isTranscriptOutputConfig_OutputType `protobuf_oneof:"output_type"`
// contains filtered or unexported fields
}
Specifies an optional destination for the recognition results.
func (*TranscriptOutputConfig) Descriptor
func (*TranscriptOutputConfig) Descriptor() ([]byte, []int)
Deprecated: Use TranscriptOutputConfig.ProtoReflect.Descriptor instead.
func (*TranscriptOutputConfig) GetGcsUri
func (x *TranscriptOutputConfig) GetGcsUri() string
func (*TranscriptOutputConfig) GetOutputType
func (m *TranscriptOutputConfig) GetOutputType() isTranscriptOutputConfig_OutputType
func (*TranscriptOutputConfig) ProtoMessage
func (*TranscriptOutputConfig) ProtoMessage()
func (*TranscriptOutputConfig) ProtoReflect
func (x *TranscriptOutputConfig) ProtoReflect() protoreflect.Message
func (*TranscriptOutputConfig) Reset
func (x *TranscriptOutputConfig) Reset()
func (*TranscriptOutputConfig) String
func (x *TranscriptOutputConfig) String() string
TranscriptOutputConfig_GcsUri
type TranscriptOutputConfig_GcsUri struct {
// Specifies a Cloud Storage URI for the recognition results. Must be
// specified in the format: `gs://bucket_name/object_name`, and the bucket
// must already exist.
GcsUri string `protobuf:"bytes,1,opt,name=gcs_uri,json=gcsUri,proto3,oneof"`
}
UnimplementedAdaptationServer
type UnimplementedAdaptationServer struct {
}
UnimplementedAdaptationServer can be embedded to have forward compatible implementations.
func (*UnimplementedAdaptationServer) CreateCustomClass
func (*UnimplementedAdaptationServer) CreateCustomClass(context.Context, *CreateCustomClassRequest) (*CustomClass, error)
func (*UnimplementedAdaptationServer) CreatePhraseSet
func (*UnimplementedAdaptationServer) CreatePhraseSet(context.Context, *CreatePhraseSetRequest) (*PhraseSet, error)
func (*UnimplementedAdaptationServer) DeleteCustomClass
func (*UnimplementedAdaptationServer) DeleteCustomClass(context.Context, *DeleteCustomClassRequest) (*emptypb.Empty, error)
func (*UnimplementedAdaptationServer) DeletePhraseSet
func (*UnimplementedAdaptationServer) DeletePhraseSet(context.Context, *DeletePhraseSetRequest) (*emptypb.Empty, error)
func (*UnimplementedAdaptationServer) GetCustomClass
func (*UnimplementedAdaptationServer) GetCustomClass(context.Context, *GetCustomClassRequest) (*CustomClass, error)
func (*UnimplementedAdaptationServer) GetPhraseSet
func (*UnimplementedAdaptationServer) GetPhraseSet(context.Context, *GetPhraseSetRequest) (*PhraseSet, error)
func (*UnimplementedAdaptationServer) ListCustomClasses
func (*UnimplementedAdaptationServer) ListCustomClasses(context.Context, *ListCustomClassesRequest) (*ListCustomClassesResponse, error)
func (*UnimplementedAdaptationServer) ListPhraseSet
func (*UnimplementedAdaptationServer) ListPhraseSet(context.Context, *ListPhraseSetRequest) (*ListPhraseSetResponse, error)
func (*UnimplementedAdaptationServer) UpdateCustomClass
func (*UnimplementedAdaptationServer) UpdateCustomClass(context.Context, *UpdateCustomClassRequest) (*CustomClass, error)
func (*UnimplementedAdaptationServer) UpdatePhraseSet
func (*UnimplementedAdaptationServer) UpdatePhraseSet(context.Context, *UpdatePhraseSetRequest) (*PhraseSet, error)
UnimplementedSpeechServer
type UnimplementedSpeechServer struct {
}
UnimplementedSpeechServer can be embedded to have forward compatible implementations.
func (*UnimplementedSpeechServer) LongRunningRecognize
func (*UnimplementedSpeechServer) LongRunningRecognize(context.Context, *LongRunningRecognizeRequest) (*longrunningpb.Operation, error)
func (*UnimplementedSpeechServer) Recognize
func (*UnimplementedSpeechServer) Recognize(context.Context, *RecognizeRequest) (*RecognizeResponse, error)
func (*UnimplementedSpeechServer) StreamingRecognize
func (*UnimplementedSpeechServer) StreamingRecognize(Speech_StreamingRecognizeServer) error
UpdateCustomClassRequest
type UpdateCustomClassRequest struct {
// Required. The custom class to update.
//
// The custom class's `name` field is used to identify the custom class to be
// updated. Format:
//
// `projects/{project}/locations/{location}/customClasses/{custom_class}`
//
// Speech-to-Text supports three locations: `global`, `us` (US North America),
// and `eu` (Europe). If you are calling the `speech.googleapis.com`
// endpoint, use the `global` location. To specify a region, use a
// [regional endpoint](https://cloud.google.com/speech-to-text/docs/endpoints)
// with matching `us` or `eu` location value.
CustomClass *CustomClass `protobuf:"bytes,1,opt,name=custom_class,json=customClass,proto3" json:"custom_class,omitempty"`
// The list of fields to be updated.
UpdateMask *fieldmaskpb.FieldMask `protobuf:"bytes,2,opt,name=update_mask,json=updateMask,proto3" json:"update_mask,omitempty"`
// contains filtered or unexported fields
}
Message sent by the client for the UpdateCustomClass
method.
func (*UpdateCustomClassRequest) Descriptor
func (*UpdateCustomClassRequest) Descriptor() ([]byte, []int)
Deprecated: Use UpdateCustomClassRequest.ProtoReflect.Descriptor instead.
func (*UpdateCustomClassRequest) GetCustomClass
func (x *UpdateCustomClassRequest) GetCustomClass() *CustomClass
func (*UpdateCustomClassRequest) GetUpdateMask
func (x *UpdateCustomClassRequest) GetUpdateMask() *fieldmaskpb.FieldMask
func (*UpdateCustomClassRequest) ProtoMessage
func (*UpdateCustomClassRequest) ProtoMessage()
func (*UpdateCustomClassRequest) ProtoReflect
func (x *UpdateCustomClassRequest) ProtoReflect() protoreflect.Message
func (*UpdateCustomClassRequest) Reset
func (x *UpdateCustomClassRequest) Reset()
func (*UpdateCustomClassRequest) String
func (x *UpdateCustomClassRequest) String() string
UpdatePhraseSetRequest
type UpdatePhraseSetRequest struct {
// Required. The phrase set to update.
//
// The phrase set's `name` field is used to identify the set to be
// updated. Format:
//
// `projects/{project}/locations/{location}/phraseSets/{phrase_set}`
//
// Speech-to-Text supports three locations: `global`, `us` (US North America),
// and `eu` (Europe). If you are calling the `speech.googleapis.com`
// endpoint, use the `global` location. To specify a region, use a
// [regional endpoint](https://cloud.google.com/speech-to-text/docs/endpoints)
// with matching `us` or `eu` location value.
PhraseSet *PhraseSet `protobuf:"bytes,1,opt,name=phrase_set,json=phraseSet,proto3" json:"phrase_set,omitempty"`
// The list of fields to be updated.
UpdateMask *fieldmaskpb.FieldMask `protobuf:"bytes,2,opt,name=update_mask,json=updateMask,proto3" json:"update_mask,omitempty"`
// contains filtered or unexported fields
}
Message sent by the client for the UpdatePhraseSet
method.
func (*UpdatePhraseSetRequest) Descriptor
func (*UpdatePhraseSetRequest) Descriptor() ([]byte, []int)
Deprecated: Use UpdatePhraseSetRequest.ProtoReflect.Descriptor instead.
func (*UpdatePhraseSetRequest) GetPhraseSet
func (x *UpdatePhraseSetRequest) GetPhraseSet() *PhraseSet
func (*UpdatePhraseSetRequest) GetUpdateMask
func (x *UpdatePhraseSetRequest) GetUpdateMask() *fieldmaskpb.FieldMask
func (*UpdatePhraseSetRequest) ProtoMessage
func (*UpdatePhraseSetRequest) ProtoMessage()
func (*UpdatePhraseSetRequest) ProtoReflect
func (x *UpdatePhraseSetRequest) ProtoReflect() protoreflect.Message
func (*UpdatePhraseSetRequest) Reset
func (x *UpdatePhraseSetRequest) Reset()
func (*UpdatePhraseSetRequest) String
func (x *UpdatePhraseSetRequest) String() string
WordInfo
type WordInfo struct {
// Time offset relative to the beginning of the audio,
// and corresponding to the start of the spoken word.
// This field is only set if `enable_word_time_offsets=true` and only
// in the top hypothesis.
// This is an experimental feature and the accuracy of the time offset can
// vary.
StartTime *durationpb.Duration `protobuf:"bytes,1,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
// Time offset relative to the beginning of the audio,
// and corresponding to the end of the spoken word.
// This field is only set if `enable_word_time_offsets=true` and only
// in the top hypothesis.
// This is an experimental feature and the accuracy of the time offset can
// vary.
EndTime *durationpb.Duration `protobuf:"bytes,2,opt,name=end_time,json=endTime,proto3" json:"end_time,omitempty"`
// The word corresponding to this set of information.
Word string `protobuf:"bytes,3,opt,name=word,proto3" json:"word,omitempty"`
// The confidence estimate between 0.0 and 1.0. A higher number
// indicates an estimated greater likelihood that the recognized words are
// correct. This field is set only for the top alternative of a non-streaming
// result or, of a streaming result where `is_final=true`.
// This field is not guaranteed to be accurate and users should not rely on it
// to be always provided.
// The default of 0.0 is a sentinel value indicating `confidence` was not set.
Confidence float32 `protobuf:"fixed32,4,opt,name=confidence,proto3" json:"confidence,omitempty"`
// Output only. A distinct integer value is assigned for every speaker within
// the audio. This field specifies which one of those speakers was detected to
// have spoken this word. Value ranges from '1' to diarization_speaker_count.
// speaker_tag is set if enable_speaker_diarization = 'true' and only in the
// top alternative.
SpeakerTag int32 `protobuf:"varint,5,opt,name=speaker_tag,json=speakerTag,proto3" json:"speaker_tag,omitempty"`
// contains filtered or unexported fields
}
Word-specific information for recognized words.
func (*WordInfo) Descriptor
Deprecated: Use WordInfo.ProtoReflect.Descriptor instead.
func (*WordInfo) GetConfidence
func (*WordInfo) GetEndTime
func (x *WordInfo) GetEndTime() *durationpb.Duration
func (*WordInfo) GetSpeakerTag
func (*WordInfo) GetStartTime
func (x *WordInfo) GetStartTime() *durationpb.Duration
func (*WordInfo) GetWord
func (*WordInfo) ProtoMessage
func (*WordInfo) ProtoMessage()
func (*WordInfo) ProtoReflect
func (x *WordInfo) ProtoReflect() protoreflect.Message
func (*WordInfo) Reset
func (x *WordInfo) Reset()