feat: Add new gcloud commands, API clients, and third-party libraries across various services.

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/speech/recognizers/__init__.py

@@ -0,0 +1,26 @@
+# -*- coding: utf-8 -*- #
+# Copyright 2022 Google LLC. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Command group for ml speech operations."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import unicode_literals
+
+from googlecloudsdk.calliope import base
+
+
+@base.ReleaseTracks(base.ReleaseTrack.ALPHA)
+class Recognizers(base.Group):
+  """Manage Google cloud speech-to-text recognizers."""

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/speech/recognizers/create.py

@@ -0,0 +1,88 @@
+# -*- coding: utf-8 -*- #
+# Copyright 2022 Google LLC. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Cloud Speech-to-text recognizers create command."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import unicode_literals
+
+from googlecloudsdk.api_lib.ml.speech import client
+from googlecloudsdk.calliope import base
+from googlecloudsdk.command_lib.ml.speech import flag_validations
+from googlecloudsdk.command_lib.ml.speech import flags_v2
+from googlecloudsdk.core import log
+
+
+@base.UniverseCompatible
+@base.ReleaseTracks(base.ReleaseTrack.ALPHA)
+class Create(base.Command):
+  """Create a speech-to-text recognizer."""
+
+  def ValidateCreateRecognizerFlags(self, args):
+    """Validates create flags."""
+    flag_validations.ValidateSpeakerDiarization(args)
+    flag_validations.ValidateDecodingConfig(args)
+
+  @staticmethod
+  def Args(parser):
+    """Register flags for this command."""
+    flags_v2.AddAllFlagsToParser(
+        parser, require_base_recognizer_attributes=True, use_store_true=True
+    )
+
+  def Run(self, args):
+    recognizer = args.CONCEPTS.recognizer.Parse()
+
+    self.ValidateCreateRecognizerFlags(args)
+
+    speech_client = client.SpeechV2Client()
+    is_async = args.async_
+
+    recognition_config, _ = speech_client.InitializeRecognitionConfig(
+        args.model, args.language_codes
+    )
+
+    recognition_config, _ = speech_client.InitializeDecodingConfigFromArgs(
+        recognition_config,
+        args,
+    )
+
+    recognition_config.features, _ = (
+        speech_client.InitializeASRFeaturesFromArgs(args)
+    )
+
+    operation = speech_client.CreateRecognizer(
+        recognizer,
+        args.display_name,
+        args.model,
+        args.language_codes,
+        recognition_config,
+    )
+
+    if is_async:
+      log.CreatedResource(
+          operation.name, kind='speech recognizer', is_async=True
+      )
+      return operation
+
+    resource = speech_client.WaitForRecognizerOperation(
+        location=recognizer.Parent().Name(),
+        operation_ref=speech_client.GetOperationRef(operation),
+        message='waiting for recognizer [{}] to be created'.format(
+            recognizer.RelativeName()
+        ),
+    )
+    log.CreatedResource(resource.name, kind='speech recognizer')
+    return resource

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/speech/recognizers/delete.py

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*- #
+# Copyright 2022 Google LLC. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Cloud Speech-to-text recognizers delete command."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import unicode_literals
+
+from googlecloudsdk.api_lib.ml.speech import client
+from googlecloudsdk.calliope import base
+from googlecloudsdk.command_lib.ml.speech import flags_v2
+from googlecloudsdk.core import log
+
+
+@base.ReleaseTracks(base.ReleaseTrack.ALPHA)
+class Delete(base.Command):
+  """Delete a Speech-to-text recognizer."""
+
+  @staticmethod
+  def Args(parser):
+    """Register flags for this command."""
+    flags_v2.AddRecognizerArgToParser(parser)
+    base.ASYNC_FLAG.AddToParser(parser)
+    base.ASYNC_FLAG.SetDefault(parser, False)
+
+  def Run(self, args):
+    recognizer = args.CONCEPTS.recognizer.Parse()
+    speech_client = client.SpeechV2Client()
+    is_async = args.async_
+    operation = speech_client.DeleteRecognizer(recognizer)
+
+    if is_async:
+      log.DeletedResource(
+          operation.name, kind='speech recognizer', is_async=True)
+      return operation
+
+    resource = speech_client.WaitForRecognizerOperation(
+        location=recognizer.Parent().Name(),
+        operation_ref=speech_client.GetOperationRef(operation),
+        message='waiting for recognizer [{}] to be deleted'.format(
+            recognizer.RelativeName()))
+    log.DeletedResource(resource.name, kind='speech recognizer')
+
+    return resource

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/speech/recognizers/describe.py

@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*- #
+# Copyright 2022 Google LLC. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Cloud Speech-to-text recognizers describe command."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import unicode_literals
+
+from googlecloudsdk.api_lib.ml.speech import client
+from googlecloudsdk.calliope import base
+from googlecloudsdk.command_lib.ml.speech import flags_v2
+
+
+@base.ReleaseTracks(base.ReleaseTrack.ALPHA)
+class Create(base.Command):
+  """Obtain details about Speech-to-text recognizer."""
+
+  @staticmethod
+  def Args(parser):
+    """Register flags for this command."""
+    flags_v2.AddRecognizerArgToParser(parser)
+
+  def Run(self, args):
+    recognizer = args.CONCEPTS.recognizer.Parse()
+    speech_client = client.SpeechV2Client()
+    return speech_client.GetRecognizer(recognizer)

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/speech/recognizers/list.py

@@ -0,0 +1,44 @@
+# -*- coding: utf-8 -*- #
+# Copyright 2022 Google LLC. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Cloud Speech-to-text recognizers list command."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import unicode_literals
+
+from googlecloudsdk.api_lib.ml.speech import client
+from googlecloudsdk.calliope import base
+from googlecloudsdk.command_lib.ml.speech import flags_v2
+
+
+@base.ReleaseTracks(base.ReleaseTrack.ALPHA)
+class Create(base.ListCommand):
+  """List Speech-to-text recognizers."""
+
+  @staticmethod
+  def Args(parser):
+    """Register flags for this command."""
+    flags_v2.AddLocationArgToParser(parser)
+    parser.display_info.AddFormat(
+        'table(name.segment(-1):label=NAME,'
+        'createTime.date(tz=LOCAL),'
+        'updateTime.date(tz=LOCAL),'
+        'model,'
+        'language_codes.join(sep=","))')
+
+  def Run(self, args):
+    location = args.CONCEPTS.location.Parse()
+    speech_client = client.SpeechV2Client()
+    return speech_client.ListRecognizers(location, limit=args.limit)

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/speech/recognizers/run_batch.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*- #
+# Copyright 2024 Google LLC. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Cloud Speech-to-text recognizers run short audio command."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import unicode_literals
+from googlecloudsdk.api_lib.ml.speech import client
+from googlecloudsdk.calliope import base
+from googlecloudsdk.command_lib.ml.speech import flag_validations
+from googlecloudsdk.command_lib.ml.speech import flags_v2
+
+
+@base.UniverseCompatible
+@base.ReleaseTracks(base.ReleaseTrack.ALPHA)
+class RunBatch(base.Command):
+  """Get transcripts of long (more than 60 seconds) audio from a gcloud uri."""
+
+  def ValidateRunBatchFlags(self, args):
+    """Validates run batch flags."""
+    flag_validations.ValidateDecodingConfig(args)
+    flag_validations.ValidateAudioSource(args, batch=True)
+
+  @staticmethod
+  def Args(parser):
+    """Register flags for this command."""
+    flags_v2.AddRecognizeRequestFlagsToParser(parser, add_async_flag=True)
+
+  def Run(self, args):
+    resource = args.CONCEPTS.recognizer.Parse()
+    speech_client = client.SpeechV2Client()
+
+    self.ValidateRunBatchFlags(args)
+
+    recognition_config_update_mask = []
+
+    recognition_config, recognition_config_update_mask = (
+        speech_client.InitializeRecognitionConfig(
+            args.model, args.language_codes, recognition_config_update_mask
+        )
+    )
+
+    recognition_config, recognition_config_update_mask = (
+        speech_client.InitializeDecodingConfigFromArgs(
+            recognition_config,
+            args,
+            default_to_auto_decoding_config=True,
+            update_mask=recognition_config_update_mask,
+        )
+    )
+
+    recognition_config.features, recognition_config_update_mask = (
+        speech_client.InitializeASRFeaturesFromArgs(
+            args, update_mask=recognition_config_update_mask
+        )
+    )
+
+    if args.hint_phrases or args.hint_phrase_sets:
+      recognition_config.adaptation, recognition_config_update_mask = (
+          speech_client.InitializeAdaptationConfigFromArgs(
+              args, update_mask=recognition_config_update_mask
+          )
+      )
+
+    operation = speech_client.RunBatch(
+        resource,
+        args.audio,
+        recognition_config,
+        update_mask=recognition_config_update_mask,
+    )
+
+    if args.async_:
+      return operation
+
+    return speech_client.WaitForBatchRecognizeOperation(
+        location=resource.Parent().Name(),
+        operation_ref=operation.name,
+        message='waiting for batch recognize to finish',
+    )

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/speech/recognizers/run_short.py

@@ -0,0 +1,82 @@
+# -*- coding: utf-8 -*- #
+# Copyright 2024 Google LLC. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Cloud Speech-to-text recognizers run short audio command."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import unicode_literals
+
+from googlecloudsdk.api_lib.ml.speech import client
+from googlecloudsdk.calliope import base
+from googlecloudsdk.command_lib.ml.speech import flag_validations
+from googlecloudsdk.command_lib.ml.speech import flags_v2
+
+
+@base.UniverseCompatible
+@base.ReleaseTracks(base.ReleaseTrack.ALPHA)
+class RunShort(base.Command):
+  """Get transcripts of short (less than 60 seconds) audio from an audio file."""
+
+  def ValidateRunShortFlags(self, args):
+    """Validates run short flags."""
+    flag_validations.ValidateDecodingConfig(args)
+    flag_validations.ValidateAudioSource(args)
+
+  @staticmethod
+  def Args(parser):
+    """Register flags for this command."""
+    flags_v2.AddRecognizeRequestFlagsToParser(parser)
+
+  def Run(self, args):
+    resource = args.CONCEPTS.recognizer.Parse()
+    speech_client = client.SpeechV2Client()
+
+    self.ValidateRunShortFlags(args)
+
+    recognition_config_update_mask = []
+
+    recognition_config, recognition_config_update_mask = (
+        speech_client.InitializeRecognitionConfig(
+            args.model, args.language_codes, recognition_config_update_mask
+        )
+    )
+
+    recognition_config, recognition_config_update_mask = (
+        speech_client.InitializeDecodingConfigFromArgs(
+            recognition_config,
+            args,
+            default_to_auto_decoding_config=True,
+            update_mask=recognition_config_update_mask,
+        )
+    )
+
+    recognition_config.features, recognition_config_update_mask = (
+        speech_client.InitializeASRFeaturesFromArgs(
+            args, update_mask=recognition_config_update_mask
+        )
+    )
+
+    if args.hint_phrases or args.hint_phrase_sets:
+      recognition_config.adaptation, recognition_config_update_mask = (
+          speech_client.InitializeAdaptationConfigFromArgs(
+              args, update_mask=recognition_config_update_mask
+          )
+      )
+
+    return speech_client.RunShort(
+        resource,
+        args.audio,
+        recognition_config,
+        recognition_config_update_mask,
+    )

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/speech/recognizers/update.py

@@ -0,0 +1,101 @@
+# -*- coding: utf-8 -*- #
+# Copyright 2022 Google LLC. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Cloud Speech-to-text recognizers update command."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import unicode_literals
+
+from googlecloudsdk.api_lib.ml.speech import client
+from googlecloudsdk.calliope import base
+from googlecloudsdk.command_lib.ml.speech import flag_validations
+from googlecloudsdk.command_lib.ml.speech import flags_v2
+from googlecloudsdk.core import log
+
+
+@base.UniverseCompatible
+@base.ReleaseTracks(base.ReleaseTrack.ALPHA)
+class Update(base.Command):
+  """Update a Speech-to-text recognizer."""
+
+  def ValidateUpdateRecognizerFlags(self, args):
+    """Validates update flags."""
+    flag_validations.ValidateDecodingConfig(args)
+
+  @staticmethod
+  def Args(parser):
+    """Register flags for this command."""
+    flags_v2.AddAllFlagsToParser(parser)
+
+  def Run(self, args):
+    recognizer = args.CONCEPTS.recognizer.Parse()
+
+    speech_client = client.SpeechV2Client()
+    is_async = args.async_
+
+    self.ValidateUpdateRecognizerFlags(args)
+
+    recognition_config_update_mask = []
+
+    recognition_config, recognition_config_update_mask = (
+        speech_client.InitializeRecognitionConfig(
+            args.model, args.language_codes, recognition_config_update_mask
+        )
+    )
+
+    recognition_config, recognition_config_update_mask = (
+        speech_client.InitializeDecodingConfigFromArgs(
+            recognition_config,
+            args,
+            update_mask=recognition_config_update_mask,
+        )
+    )
+
+    recognition_config.features, recognition_config_update_mask = (
+        speech_client.InitializeASRFeaturesFromArgs(
+            args, update_mask=recognition_config_update_mask
+        )
+    )
+
+    recognition_config_update_mask = [
+        'default_recognition_config.' + field
+        for field in recognition_config_update_mask
+    ]
+
+    operation = speech_client.UpdateRecognizer(
+        recognizer,
+        args.display_name,
+        args.model,
+        args.language_codes,
+        recognition_config,
+        update_mask=recognition_config_update_mask,
+    )
+
+    if is_async:
+      log.UpdatedResource(
+          operation.name, kind='speech recognizer', is_async=True
+      )
+      return operation
+
+    resource = speech_client.WaitForRecognizerOperation(
+        location=recognizer.Parent().Name(),
+        operation_ref=speech_client.GetOperationRef(operation),
+        message='waiting for recognizer [{}] to be updated'.format(
+            recognizer.RelativeName()
+        ),
+    )
+    log.UpdatedResource(resource.name, kind='speech recognizer')
+
+    return resource