gcloud alpha ml speech recognizers run-batch - get transcripts of long(more than 60 seconds) audio from a gcloud uri

gcloud alpha ml speech recognizers run-batch(RECOGNIZER :--location=LOCATION)--audio=AUDIO[--async][--hint-boost=HINT_BOOST][--hint-phrase-sets=[PHRASE_SET,…]][--hint-phrases=[PHRASE,…]][--language-codes=[LANGUAGE_CODE,…]][--model=MODEL][--audio-channel-count=AUDIO_CHANNEL_COUNT--encoding=ENCODING--sample-rate=SAMPLE_RATE][--[no-]enable-automatic-punctuation--[no-]enable-spoken-emojis--[no-]enable-spoken-punctuation--[no-]enable-word-confidence--[no-]enable-word-time-offsets--max-alternatives=MAX_ALTERNATIVES--[no-]profanity-filter--[no-]separate-channel-recognition--max-speaker-count=MAX_SPEAKER_COUNT--min-speaker-count=MIN_SPEAKER_COUNT][GCLOUD_WIDE_FLAG …]

Recognizer resource - recognizer. The arguments in this group can be used tospecify the attributes of this resource. (NOTE) Some attributes are not givenarguments in this group but can be set in other ways.

To set theproject attribute:

• provide the argumentrecognizer on the command line with a fullyspecified name;
• provide the argument--project on the command line;
• set the propertycore/project.

This must be specified.

RECOGNIZER

ID of the recognizer or fully qualified identifier for the recognizer.

To set therecognizer attribute:

• provide the argumentrecognizer on the command line.

This positional argument must be specified if any of the other arguments in thisgroup are specified.

--location=LOCATION

Location of the recognizer.To set thelocation attribute:

• provide the argumentrecognizer on the command line with a fullyspecified name;
• provide the argument--location on the command line.

--audio=AUDIO

Location of the audio file to transcribe. Must be a audio data bytes, localfile, or Google Cloud Storage URL (in the format gs://bucket/object).

--async

Return immediately, without waiting for the operation in progress to complete.The default isFalse.

--hint-boost=HINT_BOOST

Boost value for the phrases passed to --phrases. Can have a value between 1 and20.

--hint-phrase-sets=[PHRASE_SET,…]

A list of phrase set resource names to use for speech recognition.

--hint-phrases=[PHRASE,…]

A list of strings containing word and phrase "hints" so that the ' 'speechrecognition is more likely to recognize them. This can be ' 'used to improve theaccuracy for specific words and phrases, ' 'for example, if specific commandsare typically spoken by ' 'the user. This can also be used to add additionalwords to the ' 'vocabulary of the recognizer. ' 'Seehttps://cloud.google.com/speech/limits#content.

--language-codes=[LANGUAGE_CODE,…]

Language code is one ofen-US,en-GB,fr-FR. Checkdocumentationfor using more than one language code.

--model=MODEL

Which model to use for recognition requests. Select the model best suited toyour domain to get best results. Guidance for choosing which model to use can befound in theTranscriptionModels Documentation and the models supported in each region can be found intheTableOf Supported Models.

Encoding format

--audio-channel-count=AUDIO_CHANNEL_COUNT

Number of channels present in the audio data sent for recognition. Required if--encoding flag is specified and is not AUTO. Must be set to a value between 1and 8.

--encoding=ENCODING

Encoding format of the provided audio. For headerless formats, must be set toLINEAR16,MULAW, orALAW. For otherformats, set toAUTO. Overrides the recognizer configuration ifpresent, else uses recognizer encoding.

--sample-rate=SAMPLE_RATE

Sample rate in Hertz of the audio data sent for recognition. Required if--encoding flag is specified and is not AUTO. Must be set to a value between8000 and 48000.

ASR Features

--[no-]enable-automatic-punctuation

If set, adds punctuation to recognition result hypotheses. Use--enable-automatic-punctuation to enable and--no-enable-automatic-punctuation to disable.

--[no-]enable-spoken-emojis

If set, adds spoken emoji formatting. Use--enable-spoken-emojis toenable and--no-enable-spoken-emojis to disable.

--[no-]enable-spoken-punctuation

If set, replaces spoken punctuation with the corresponding symbols in therequest. Use--enable-spoken-punctuation to enable and--no-enable-spoken-punctuation to disable.

--[no-]enable-word-confidence

If set, the top result includes a list of words and the confidence for thosewords. Use--enable-word-confidence to enable and--no-enable-word-confidence to disable.

--[no-]enable-word-time-offsets

If set, the top result includes a list of words and their timestamps. Use--enable-word-time-offsets to enable and--no-enable-word-time-offsets to disable.

--max-alternatives=MAX_ALTERNATIVES

Maximum number of recognition hypotheses to be returned. Must be set to a valuebetween 1 and 30.

--[no-]profanity-filter

If set, the server will censor profanities. Use--profanity-filterto enable and--no-profanity-filter to disable.

--[no-]separate-channel-recognition

Mode for recognizing multi-channel audio using Separate Channel Recognition.When set, the service will recognize each channel independently. Use--separate-channel-recognition to enable and--no-separate-channel-recognition to disable.

Speaker Diarization

--max-speaker-count=MAX_SPEAKER_COUNT

Maximum number of speakers in the conversation. Must be greater than or equal to--min-speaker-count. Must be set to a value between 1 and 6.

This flag argument must be specified if any of the other arguments in this groupare specified.

--min-speaker-count=MIN_SPEAKER_COUNT

Minimum number of speakers in the conversation. Must be less than or equal to--max-speaker-count. Must be set to a value between 1 and 6.

This flag argument must be specified if any of the other arguments in this groupare specified.

Run$gcloud help for details.