Performs asynchronous video annotation. Progress and results can be
annotate(body, x__xgafv=None)
Performs asynchronous video annotation. Progress and results can be
retrieved through the `google.longrunning.Operations` interface.
`Operation.metadata` contains `AnnotateVideoProgress` (progress).
`Operation.response` contains `AnnotateVideoResponse` (results).
Args:
body: object, The request body. (required)
The object takes the form of:
{ # Video annotation request.
"videoContext": { # Video context and/or feature-specific parameters. # Additional video context and/or feature-specific parameters.
"shotChangeDetectionConfig": { # Config for SHOT_CHANGE_DETECTION. # Config for SHOT_CHANGE_DETECTION.
"model": "A String", # Model to use for shot change detection.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
},
"textDetectionConfig": { # Config for TEXT_DETECTION. # Config for TEXT_DETECTION.
"languageHints": [ # Language hint can be specified if the language to be detected is known a
# priori. It can increase the accuracy of the detection. Language hint must
# be language code in BCP-47 format.
#
# Automatic language detection is performed if no hint is provided.
"A String",
],
"model": "A String", # Model to use for text detection.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
},
"speechTranscriptionConfig": { # Config for SPEECH_TRANSCRIPTION. # Config for SPEECH_TRANSCRIPTION.
"languageCode": "A String", # *Required* The language of the supplied audio as a
# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
# Example: "en-US".
# See [Language Support](https://cloud.google.com/speech/docs/languages)
# for a list of the currently supported language codes.
"filterProfanity": True or False, # *Optional* If set to `true`, the server will attempt to filter out
# profanities, replacing all but the initial character in each filtered word
# with asterisks, e.g. "f***". If set to `false` or omitted, profanities
# won't be filtered out.
"enableAutomaticPunctuation": True or False, # *Optional* If 'true', adds punctuation to recognition result hypotheses.
# This feature is only available in select languages. Setting this for
# requests in other languages has no effect at all. The default 'false' value
# does not add punctuation to result hypotheses. NOTE: "This is currently
# offered as an experimental service, complimentary to all users. In the
# future this may be exclusively available as a premium feature."
"enableSpeakerDiarization": True or False, # *Optional* If 'true', enables speaker detection for each recognized word in
# the top alternative of the recognition result using a speaker_tag provided
# in the WordInfo.
# Note: When this is true, we send all the words from the beginning of the
# audio for the top alternative in every consecutive responses.
# This is done in order to improve our speaker tags as our models learn to
# identify the speakers in the conversation over time.
"maxAlternatives": 42, # *Optional* Maximum number of recognition hypotheses to be returned.
# Specifically, the maximum number of `SpeechRecognitionAlternative` messages
# within each `SpeechTranscription`. The server may return fewer than
# `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will
# return a maximum of one. If omitted, will return a maximum of one.
"audioTracks": [ # *Optional* For file formats, such as MXF or MKV, supporting multiple audio
# tracks, specify up to two tracks. Default: track 0.
42,
],
"diarizationSpeakerCount": 42, # *Optional*
# If set, specifies the estimated number of speakers in the conversation.
# If not set, defaults to '2'.
# Ignored unless enable_speaker_diarization is set to true.
"enableWordConfidence": True or False, # *Optional* If `true`, the top result includes a list of words and the
# confidence for those words. If `false`, no word-level confidence
# information is returned. The default is `false`.
"speechContexts": [ # *Optional* A means to provide context to assist the speech recognition.
{ # Provides "hints" to the speech recognizer to favor specific words and phrases
# in the results.
"phrases": [ # *Optional* 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/limits#content).
"A String",
],
},
],
},
"segments": [ # Video segments to annotate. The segments may overlap and are not required
# to be contiguous or span the whole video. If unspecified, each video is
# treated as a single segment.
{ # Video segment.
"endTimeOffset": "A String", # Time-offset, relative to the beginning of the video,
# corresponding to the end of the segment (inclusive).
"startTimeOffset": "A String", # Time-offset, relative to the beginning of the video,
# corresponding to the start of the segment (inclusive).
},
],
"labelDetectionConfig": { # Config for LABEL_DETECTION. # Config for LABEL_DETECTION.
"labelDetectionMode": "A String", # What labels should be detected with LABEL_DETECTION, in addition to
# video-level labels or segment-level labels.
# If unspecified, defaults to `SHOT_MODE`.
"model": "A String", # Model to use for label detection.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
"stationaryCamera": True or False, # Whether the video has been shot from a stationary (i.e. non-moving) camera.
# When set to true, might improve detection accuracy for moving objects.
# Should be used with `SHOT_AND_FRAME_MODE` enabled.
"frameConfidenceThreshold": 3.14, # The confidence threshold we perform filtering on the labels from
# frame-level detection. If not set, it is set to 0.4 by default. The valid
# range for this threshold is [0.1, 0.9]. Any value set outside of this
# range will be clipped.
# Note: for best results please follow the default threshold. We will update
# the default threshold everytime when we release a new model.
"videoConfidenceThreshold": 3.14, # The confidence threshold we perform filtering on the labels from
# video-level and shot-level detections. If not set, it is set to 0.3 by
# default. The valid range for this threshold is [0.1, 0.9]. Any value set
# outside of this range will be clipped.
# Note: for best results please follow the default threshold. We will update
# the default threshold everytime when we release a new model.
},
"explicitContentDetectionConfig": { # Config for EXPLICIT_CONTENT_DETECTION. # Config for EXPLICIT_CONTENT_DETECTION.
"model": "A String", # Model to use for explicit content detection.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
},
"objectTrackingConfig": { # Config for OBJECT_TRACKING. # Config for OBJECT_TRACKING.
"model": "A String", # Model to use for object tracking.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
},
},
"features": [ # Requested video annotation features.
"A String",
],
"inputContent": "A String", # The video data bytes.
# If unset, the input video(s) should be specified via `input_uri`.
# If set, `input_uri` should be unset.
"inputUri": "A String", # Input video location. Currently, only
# [Google Cloud Storage](https://cloud.google.com/storage/) URIs are
# supported, which must be specified in the following format:
# `gs://bucket-id/object-id` (other URI formats return
# google.rpc.Code.INVALID_ARGUMENT). For more information, see
# [Request URIs](/storage/docs/reference-uris).
# A video URI may include wildcards in `object-id`, and thus identify
# multiple videos. Supported wildcards: '*' to match 0 or more characters;
# '?' to match 1 character. If unset, the input video should be embedded
# in the request as `input_content`. If set, `input_content` should be unset.
"locationId": "A String", # Optional cloud region where annotation should take place. Supported cloud
# regions: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region
# is specified, a region will be determined based on video file location.
"outputUri": "A String", # Optional location where the output (in JSON format) should be stored.
# Currently, only [Google Cloud Storage](https://cloud.google.com/storage/)
# URIs are supported, which must be specified in the following format:
# `gs://bucket-id/object-id` (other URI formats return
# google.rpc.Code.INVALID_ARGUMENT). For more information, see
# [Request URIs](/storage/docs/reference-uris).
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a
# network API call.
"metadata": { # Service-specific metadata associated with the operation. It typically
# contains progress information and common metadata such as create time.
# Some services might not provide such metadata. Any method that returns a
# long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"done": True or False, # If the value is `false`, it means the operation is still in progress.
# If `true`, the operation is completed, and either `error` or `response` is
# available.
"response": { # The normal response of the operation in case of success. If the original
# method returns no data on success, such as `Delete`, the response is
# `google.protobuf.Empty`. If the original method is standard
# `Get`/`Create`/`Update`, the response should be the resource. For other
# methods, the response should have the type `XxxResponse`, where `Xxx`
# is the original method name. For example, if the original method name
# is `TakeSnapshot()`, the inferred response type is
# `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that
# originally returns it. If you use the default HTTP mapping, the
# `name` should be a resource name ending with `operations/{unique_id}`.
"error": { # The `Status` type defines a logical error model that is suitable for # The error result of the operation in case of failure or cancellation.
# different programming environments, including REST APIs and RPC APIs. It is
# used by [gRPC](https://github.com/grpc). Each `Status` message contains
# three pieces of data: error code, error message, and error details.
#
# You can find out more about this error model and how to work with it in the
# [API Design Guide](https://cloud.google.com/apis/design/errors).
"message": "A String", # A developer-facing error message, which should be in English. Any
# user-facing error message should be localized and sent in the
# google.rpc.Status.details field, or localized by the client.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of
# message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
},
}