chore: librarian generate pull request: 20260107T084051Z (#14995) · googleapis/google-cloud-python@b3cb4de
@@ -38,6 +38,7 @@
3838"AutoDetectDecodingConfig",
3939"ExplicitDecodingConfig",
4040"SpeakerDiarizationConfig",
41+"CustomPromptConfig",
4142"RecognitionFeatures",
4243"TranscriptNormalization",
4344"TranslationConfig",
@@ -898,17 +899,13 @@ class SpeakerDiarizationConfig(proto.Message):
898899899900 Attributes:
900901 min_speaker_count (int):
901- Required. Minimum number of speakers in the conversation.
902- This range gives you more flexibility by allowing the system
903- to automatically determine the correct number of speakers.
904-905- To fix the number of speakers detected in the audio, set
906- ``min_speaker_count`` = ``max_speaker_count``.
902+ Optional. The system automatically determines
903+ the number of speakers. This value is not
904+ currently used.
907905 max_speaker_count (int):
908- Required. Maximum number of speakers in the conversation.
909- Valid values are: 1-6. Must be >= ``min_speaker_count``.
910- This range gives you more flexibility by allowing the system
911- to automatically determine the correct number of speakers.
906+ Optional. The system automatically determines
907+ the number of speakers. This value is not
908+ currently used.
912909 """
913910914911min_speaker_count: int = proto.Field(
@@ -921,6 +918,21 @@ class SpeakerDiarizationConfig(proto.Message):
921918 )
922919923920921+class CustomPromptConfig(proto.Message):
922+r"""Configuration to enable custom prompt in chirp3.
923+924+ Attributes:
925+ custom_prompt (str):
926+ Optional. The custom instructions to override
927+ the existing instructions for chirp3.
928+ """
929+930+custom_prompt: str = proto.Field(
931+proto.STRING,
932+number=1,
933+ )
934+935+924936class RecognitionFeatures(proto.Message):
925937r"""Available recognition features.
926938@@ -962,24 +974,18 @@ class RecognitionFeatures(proto.Message):
962974 multi_channel_mode (google.cloud.speech_v2.types.RecognitionFeatures.MultiChannelMode):
963975 Mode for recognizing multi-channel audio.
964976 diarization_config (google.cloud.speech_v2.types.SpeakerDiarizationConfig):
965- Configuration to enable speaker diarization
966- and set additional parameters to make
967- diarization better suited for your application.
968- When this is enabled, we send all the words from
969- the beginning of the audio for the top
970- alternative in every consecutive STREAMING
971- responses. This is done in order to improve our
972- speaker tags as our models learn to identify the
973- speakers in the conversation over time. For
974- non-streaming requests, the diarization results
975- will be provided only in the top alternative of
976- the FINAL SpeechRecognitionResult.
977+ Configuration to enable speaker diarization.
978+ To enable diarization, set this field to an
979+ empty SpeakerDiarizationConfig message.
977980 max_alternatives (int):
978981 Maximum number of recognition hypotheses to be returned. The
979982 server may return fewer than ``max_alternatives``. Valid
980983 values are ``0``-``30``. A value of ``0`` or ``1`` will
981984 return a maximum of one. If omitted, will return a maximum
982985 of one.
986+ custom_prompt_config (google.cloud.speech_v2.types.CustomPromptConfig):
987+ Optional. Configuration to enable custom
988+ prompt for chirp3.
983989 """
984990985991class MultiChannelMode(proto.Enum):
@@ -1038,6 +1044,11 @@ class MultiChannelMode(proto.Enum):
10381044proto.INT32,
10391045number=16,
10401046 )
1047+custom_prompt_config: "CustomPromptConfig" = proto.Field(
1048+proto.MESSAGE,
1049+number=18,
1050+message="CustomPromptConfig",
1051+ )
104110521042105310431054class TranscriptNormalization(proto.Message):
@@ -1410,13 +1421,20 @@ class RecognizeRequest(proto.Message):
14101421class RecognitionResponseMetadata(proto.Message):
14111422r"""Metadata about the recognition request and response.
141214231424+ .. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields
1425+14131426 Attributes:
14141427 request_id (str):
14151428 Global request identifier auto-generated by
14161429 the API.
14171430 total_billed_duration (google.protobuf.duration_pb2.Duration):
14181431 When available, billed audio seconds for the
14191432 corresponding request.
1433+ prompt (str):
1434+ Optional. Output only. Provides the prompt
1435+ used for the recognition request.
1436+1437+ This field is a member of `oneof`_ ``_prompt``.
14201438 """
1421143914221440request_id: str = proto.Field(
@@ -1428,6 +1446,11 @@ class RecognitionResponseMetadata(proto.Message):
14281446number=6,
14291447message=duration_pb2.Duration,
14301448 )
1449+prompt: str = proto.Field(
1450+proto.STRING,
1451+number=10,
1452+optional=True,
1453+ )
143114541432145514331456class SpeechRecognitionAlternative(proto.Message):