- NAME
-
- gcloud beta ml video transcribe-speech - transcribe speech in a video
- SYNOPSIS
-
-
gcloud beta ml video transcribe-speech
INPUT_PATH
--language-code
=LANGUAGE_CODE
[--async
] [--audio-tracks
=[AUDIO_TRACKS
,…]] [--diarization-speaker-count
=DIARIZATION_SPEAKER_COUNT
] [--enable-automatic-punctuation
] [--enable-speaker-diarization
] [--enable-word-confidence
] [--filter-profanity
] [--hints
=[HINTS
,…]] [--max-alternatives
=MAX_ALTERNATIVES
] [--output-uri
=OUTPUT_URI
] [--region
=REGION
] [--segments
=[SEGMENTS
,…]] [GCLOUD_WIDE_FLAG …
]
-
- DESCRIPTION
-
(BETA)
Transcribe speech within a video. - EXAMPLES
-
To transcribe speech in video file 'gs://my_bucket/input_file.mp4':
gcloud beta ml video transcribe-speech gs://my_bucket/input_file.mp4
- POSITIONAL ARGUMENTS
-
INPUT_PATH
- Path to the video to be analyzed. Must be a local path or a Google Cloud Storage URI.
- REQUIRED FLAGS
-
--language-code
=LANGUAGE_CODE
- The language of the supplied audio as a BCP-47 language tag. Example: "en-US". See Language Support for a list of the currently supported language codes.
- OPTIONAL FLAGS
-
--async
- Return immediately, without waiting for the operation in progress to complete.
--audio-tracks
=[AUDIO_TRACKS
,…]- For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two commas separated tracks. Default track is 0.
--diarization-speaker-count
=DIARIZATION_SPEAKER_COUNT
- Optional estimated number of speakers in the conversation. If not specified, defaults to '2'. Ignored unless --enable-speaker-diarization is enabled.
--enable-automatic-punctuation
- If enabled, 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 disabled case does not add punctuation to result hypotheses.
--enable-speaker-diarization
- If enabled, perform speaker detection for each recognized word in the top alternative of the recognition result using a speaker_tag provided in the WordInfo results section. When this is enabled, 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.
--enable-word-confidence
- If enabled, the top result includes a list of words and the confidence for those words. If disabled, no word-level confidence information is returned. The default is disabled.
--filter-profanity
-
If enabled, the server will attempt to filter out profanities, replacing all but
the initial character in each filtered word with asterisks, e.g.
f***
. If disabled or omitted, profanities will not be filtered out. --hints
=[HINTS
,…]- 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 (https://cloud.google.com/speech/limits#content).
--max-alternatives
=MAX_ALTERNATIVES
-
Maximum number of recognition hypotheses to be returned. Specifically, the
maximum number of
SpeechRecognitionAlternative
messages within eachSpeechTranscription
. The server may return fewer thanmax_alternatives
. Valid values are0
-30
. A value of0
or1
will return a maximum of one. If omitted, will return a maximum of one --output-uri
=OUTPUT_URI
- Location to which the results should be written. Must be a Google Cloud Storage URI.
--region
=REGION
-
Optional Cloud region where annotation should take place. If no region is
specified, a region will be determined based on video file location.
REGION
must be one of:asia-east1
,europe-west1
,us-east1
,us-west1
. --segments
=[SEGMENTS
,…]-
Segments from the video which you want to analyze (by default, the entire video
will be treated as one segment). Must be in the format
START1:END1[,START2:END2,…] (inclusive). START and END of segments must
be a properly formatted duration string of the form
HhMmSs
where:* H is the number of hours from beginning of video * M is the number of minutes from the beginning of video * S is the number of seconds from the beginning of the video
H, M and S can be specified as ints or floats for fractional units (to microsecond resolution). Unit chars (e.g.
h
,m
ors
) are required. Microseconds can be specified using fractional seconds e.g. 0.000569s == 569 microseconds.Examples:
0s:23.554048s,24s:29.528064s
0:1m40s,3m50s:5m10.232265s
- GCLOUD WIDE FLAGS
-
These flags are available to all commands:
--access-token-file
,--account
,--billing-project
,--configuration
,--flags-file
,--flatten
,--format
,--help
,--impersonate-service-account
,--log-http
,--project
,--quiet
,--trace-token
,--user-output-enabled
,--verbosity
.Run
$ gcloud help
for details. - API REFERENCE
-
This command uses the
videointelligence/v1
API. The full documentation for this API can be found at: https://cloud.google.com/video-intelligence/docs/ - NOTES
-
This command is currently in beta and might change without notice. This variant
is also available:
gcloud alpha ml video transcribe-speech
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2024-02-06 UTC.