rime-api 0.2.0__tar.gz → 0.3.0__tar.gz

{rime_api-0.2.0 → rime_api-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rime-api
-Version: 0.2.0
+Version: 0.3.0
 Summary: Generated protocol definitions for Rime text-to-speech and speech-to-text
 Project-URL: Documentation, https://docs.rime.ai
 Project-URL: Repository, https://github.com/rimelabs/rime-api

{rime_api-0.2.0 → rime_api-0.3.0}/SOURCE.json

@@ -1,8 +1,8 @@
 {
-  "version": "0.2.0",
+  "version": "0.3.0",
   "schemas": {
     "rime/speech_to_text.proto": "77131e17e7048cd989d547ff81c991151c23b896272b6bff903bd548eb8eb5b3",
-    "rime/text_to_speech.proto": "6a5707f207c95fcb32557f4b811e30fb67c01df8fc4dc60ec823e592cc477e5e",
+    "rime/text_to_speech.proto": "964fb10df76a61b2ab89d0590f3f4922b49124bd3d12979a3790f65d837fe4e3",
     "speech_to_text.asyncapi.yaml": "604cb549319ff1bc7cc792d4a6df15dd8d9d75123397d57a3f31e8e5d93b71b6",
     "text_to_speech.asyncapi.yaml": "00e1223faf9858c278046bf774cf9f328606cfc336b02c71fdbf52c82a85ee35"
   }

{rime_api-0.2.0 → rime_api-0.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "rime-api"
-version = "0.2.0"
+version = "0.3.0"
 description = "Generated protocol definitions for Rime text-to-speech and speech-to-text"
 readme = "README.md"
 requires-python = ">=3.10"

{rime_api-0.2.0 → rime_api-0.3.0}/schema/rime/text_to_speech.proto

@@ -60,6 +60,22 @@ message SynthesisRequest {
   // Timestamps of the spoken spans of the synthesized audio, delivered in
   // the trailer once the audio has drained. Off unless requested.
   optional TimestampOptions timestamps = 10;
+
+  // Per-request pronunciation overrides. Validated against the request
+  // language's phonology (an ill-formed entry fails the request) and applied by
+  // the segmenter and the pronunciation stages. See
+  // engine/src/pipeline/pronunciation.rs.
+  repeated PronunciationEntry custom_lexicon = 11;
+}
+
+// One custom-lexicon pronunciation override. The neural backend speaks
+// `spelling` (matched case-insensitively as a whole word) using `pronunciation`
+// wherever it occurs in the request text.
+message PronunciationEntry {
+  // The word to override, e.g. "cache".
+  string spelling = 1;
+  // Its X-SAMPA pronunciation, e.g. `" k { S` (primary stress, then phones).
+  string pronunciation = 2;
 }
 
 message SynthesisResponseStream {
@@ -164,6 +180,10 @@ message NormalizeTextRequest {
 
   // BCP-47 language tag, e.g. "en".
   optional string language = 2;
+
+  // Per-request pronunciation overrides; same shape and validation as on
+  // SynthesisRequest.
+  repeated PronunciationEntry custom_lexicon = 3;
 }
 
 message NormalizeTextResponse {

rime_api-0.3.0/src/rime_api/text_to_speech_pb2.py

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*-
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# NO CHECKED-IN PROTOBUF GENCODE
+# source: rime_api/text_to_speech.proto
+# Protobuf Python Version: 5.29.0
+"""Generated protocol buffer code."""
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import descriptor_pool as _descriptor_pool
+from google.protobuf import runtime_version as _runtime_version
+from google.protobuf import symbol_database as _symbol_database
+from google.protobuf.internal import builder as _builder
+_runtime_version.ValidateProtobufRuntimeVersion(
+    _runtime_version.Domain.PUBLIC,
+    5,
+    29,
+    0,
+    '',
+    'rime_api/text_to_speech.proto'
+)
+# @@protoc_insertion_point(imports)
+
+_sym_db = _symbol_database.Default()
+
+
+from google.protobuf import duration_pb2 as google_dot_protobuf_dot_duration__pb2
+from google.rpc import status_pb2 as google_dot_rpc_dot_status__pb2
+
+
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\x1drime_api/text_to_speech.proto\x12\x04rime\x1a\x1egoogle/protobuf/duration.proto\x1a\x17google/rpc/status.proto\"s\n\x19StreamingSynthesisRequest\x12(\n\x06header\x18\x01 \x01(\x0b\x32\x16.rime.SynthesisRequestH\x00\x12\x14\n\ntext_chunk\x18\x02 \x01(\tH\x00\x42\t\n\x07payloadJ\x04\x08\x03\x10\x04R\x05\x66lush\"\x97\x04\n\x10SynthesisRequest\x12\x15\n\x08language\x18\x02 \x01(\tH\x00\x88\x01\x01\x12\x14\n\x07speaker\x18\x03 \x01(\tH\x01\x88\x01\x01\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x34\n\x10\x61udio_parameters\x18\x05 \x01(\x0b\x32\x15.rime.AudioParametersH\x02\x88\x01\x01\x12\x30\n\x0esplit_strategy\x18\x06 \x01(\x0e\x32\x13.rime.SplitStrategyH\x03\x88\x01\x01\x12\x32\n\x0f\x63oda_parameters\x18\x08 \x01(\x0b\x32\x14.rime.CodaParametersH\x04\x88\x01\x01\x12\x32\n\x0fmist_parameters\x18\t \x01(\x0b\x32\x14.rime.MistParametersH\x05\x88\x01\x01\x12/\n\ntimestamps\x18\n \x01(\x0b\x32\x16.rime.TimestampOptionsH\x06\x88\x01\x01\x12\x30\n\x0e\x63ustom_lexicon\x18\x0b \x03(\x0b\x32\x18.rime.PronunciationEntryB\x0b\n\t_languageB\n\n\x08_speakerB\x13\n\x11_audio_parametersB\x11\n\x0f_split_strategyB\x12\n\x10_coda_parametersB\x12\n\x10_mist_parametersB\r\n\x0b_timestampsJ\x04\x08\x01\x10\x02J\x04\x08\x07\x10\x08R\x11\x61rcana_parameters\"=\n\x12PronunciationEntry\x12\x10\n\x08spelling\x18\x01 \x01(\t\x12\x15\n\rpronunciation\x18\x02 \x01(\t\"h\n\x17SynthesisResponseStream\x12\x0f\n\x05\x61udio\x18\x01 \x01(\x0cH\x00\x12\x31\n\x07trailer\x18\x02 \x01(\x0b\x32\x1e.rime.SynthesisResponseTrailerH\x00\x42\t\n\x07payload\"T\n\x18SynthesisResponseTrailer\x12)\n\ntimestamps\x18\x01 \x01(\x0b\x32\x10.rime.TimestampsH\x00\x88\x01\x01\x42\r\n\x0b_timestamps\"\xa1\x01\n\x0f\x41udioParameters\x12\x19\n\x0c\x61udio_format\x18\x01 \x01(\tH\x00\x88\x01\x01\x12\x1a\n\rsampling_rate\x18\x02 \x01(\x05H\x01\x88\x01\x01\x12\x1e\n\x11time_scale_factor\x18\x03 \x01(\x02H\x02\x88\x01\x01\x42\x0f\n\r_audio_formatB\x10\n\x0e_sampling_rateB\x14\n\x12_time_scale_factor\"\xc5\x01\n\x0e\x43odaParameters\x12\"\n\x15text_lookahead_tokens\x18\x08 \x01(\x05H\x00\x88\x01\x01\x42\x18\n\x16_text_lookahead_tokensJ\x04\x08\x01\x10\x02J\x04\x08\x02\x10\x03J\x04\x08\x03\x10\x04J\x04\x08\x04\x10\x05J\x04\x08\x05\x10\x06J\x04\x08\x06\x10\x07J\x04\x08\x07\x10\x08R\x0btemperatureR\x05top_kR\x05top_pR\x12repetition_penaltyR\nmax_tokensR\nmin_tokensR\x04seed\"\xe1\x01\n\x0eMistParameters\x12#\n\x16pause_between_brackets\x18\x01 \x01(\x08H\x00\x88\x01\x01\x12\'\n\x1aphonemize_between_brackets\x18\x02 \x01(\x08H\x01\x88\x01\x01\x12!\n\x19inline_time_scale_factors\x18\x03 \x03(\x02\x12\x16\n\tsave_oovs\x18\x04 \x01(\x08H\x02\x88\x01\x01\x42\x19\n\x17_pause_between_bracketsB\x1d\n\x1b_phonemize_between_bracketsB\x0c\n\n_save_oovs\"\"\n\x10TimestampOptions\x12\x0e\n\x06\x65nable\x18\x01 \x01(\x08\"o\n\rSpanTimestamp\x12\x0c\n\x04text\x18\x01 \x01(\t\x12(\n\x05start\x18\x02 \x01(\x0b\x32\x19.google.protobuf.Duration\x12&\n\x03\x65nd\x18\x03 \x01(\x0b\x32\x19.google.protobuf.Duration\"T\n\nTimestamps\x12\"\n\x06status\x18\x01 \x01(\x0b\x32\x12.google.rpc.Status\x12\"\n\x05spans\x18\x02 \x03(\x0b\x32\x13.rime.SpanTimestamp\"z\n\x14NormalizeTextRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\x15\n\x08language\x18\x02 \x01(\tH\x00\x88\x01\x01\x12\x30\n\x0e\x63ustom_lexicon\x18\x03 \x03(\x0b\x32\x18.rime.PronunciationEntryB\x0b\n\t_language\"N\n\x15NormalizeTextResponse\x12\x17\n\x0fnormalized_text\x18\x01 \x01(\t\x12\x1c\n\x14normalized_sentences\x18\x02 \x03(\t\"\x1e\n\x1cGetSupportedLanguagesRequest\"2\n\x1dGetSupportedLanguagesResponse\x12\x11\n\tlanguages\x18\x01 \x03(\t\"A\n\x1bGetSupportedSpeakersRequest\x12\x15\n\x08language\x18\x01 \x01(\tH\x00\x88\x01\x01\x42\x0b\n\t_language\"0\n\x1cGetSupportedSpeakersResponse\x12\x10\n\x08speakers\x18\x01 \x03(\t\"\xec\x01\n\x10WebSocketRequest\x12\x12\n\ncontext_id\x18\x01 \x01(\t\x12\'\n\x06\x63onfig\x18\x02 \x01(\x0b\x32\x15.rime.WebSocketConfigH\x00\x12\'\n\x05start\x18\x03 \x01(\x0b\x32\x16.rime.SynthesisRequestH\x00\x12\x0e\n\x04text\x18\x04 \x01(\tH\x00\x12!\n\x03\x65nd\x18\x05 \x01(\x0b\x32\x12.rime.WebSocketEndH\x00\x12\'\n\x06\x63\x61ncel\x18\x06 \x01(\x0b\x32\x15.rime.WebSocketCancelH\x00\x42\t\n\x07payloadJ\x04\x08\x07\x10\x08R\x05\x66lush\"\x9d\x01\n\x0fWebSocketConfig\x12\x1a\n\rauthorization\x18\x01 \x01(\tH\x00\x88\x01\x01\x12\x14\n\x07license\x18\x02 \x01(\tH\x01\x88\x01\x01\x12-\n\x08\x64\x65\x66\x61ults\x18\x03 \x01(\x0b\x32\x16.rime.SynthesisRequestH\x02\x88\x01\x01\x42\x10\n\x0e_authorizationB\n\n\x08_licenseB\x0b\n\t_defaults\"\x0e\n\x0cWebSocketEnd\"\x11\n\x0fWebSocketCancel\"\x90\x02\n\x11WebSocketResponse\x12\x12\n\ncontext_id\x18\x01 \x01(\t\x12%\n\x05ready\x18\x02 \x01(\x0b\x32\x14.rime.WebSocketReadyH\x00\x12)\n\x07started\x18\x03 \x01(\x0b\x32\x16.rime.WebSocketStartedH\x00\x12\x0f\n\x05\x61udio\x18\x04 \x01(\x0cH\x00\x12#\n\x04\x64one\x18\x05 \x01(\x0b\x32\x13.rime.WebSocketDoneH\x00\x12-\n\tcancelled\x18\x06 \x01(\x0b\x32\x18.rime.WebSocketCancelledH\x00\x12%\n\x05\x65rror\x18\x07 \x01(\x0b\x32\x14.rime.WebSocketErrorH\x00\x42\t\n\x07payload\"i\n\x0eWebSocketReady\x12\x10\n\x08protocol\x18\x01 \x01(\r\x12\x11\n\tlanguages\x18\x02 \x03(\t\x12\x1d\n\x10\x64\x65\x66\x61ult_language\x18\x03 \x01(\tH\x00\x88\x01\x01\x42\x13\n\x11_default_language\"&\n\x10WebSocketStarted\x12\x12\n\nrequest_id\x18\x01 \x01(\t\"I\n\rWebSocketDone\x12)\n\ntimestamps\x18\x01 \x01(\x0b\x32\x10.rime.TimestampsH\x00\x88\x01\x01\x42\r\n\x0b_timestamps\"\x14\n\x12WebSocketCancelled\"W\n\x0eWebSocketError\x12\x0c\n\x04kind\x18\x01 \x01(\t\x12\x0f\n\x07message\x18\x02 \x01(\t\x12\x17\n\nrequest_id\x18\x03 \x01(\tH\x00\x88\x01\x01\x42\r\n\x0b_request_id*\x8d\x01\n\rSplitStrategy\x12\x1e\n\x1aSPLIT_STRATEGY_UNSPECIFIED\x10\x00\x12\x1b\n\x17SPLIT_STRATEGY_SENTENCE\x10\x01\x12\x17\n\x13SPLIT_STRATEGY_NONE\x10\x02\x12&\n\"SPLIT_STRATEGY_ACCUMULATE_SENTENCE\x10\x03\x32\xc5\x03\n\x0cTextToSpeech\x12G\n\nSynthesize\x12\x16.rime.SynthesisRequest\x1a\x1d.rime.SynthesisResponseStream\"\x00\x30\x01\x12[\n\x13SynthesizeStreaming\x12\x1f.rime.StreamingSynthesisRequest\x1a\x1d.rime.SynthesisResponseStream\"\x00(\x01\x30\x01\x12J\n\rNormalizeText\x12\x1a.rime.NormalizeTextRequest\x1a\x1b.rime.NormalizeTextResponse\"\x00\x12\x62\n\x15GetSupportedLanguages\x12\".rime.GetSupportedLanguagesRequest\x1a#.rime.GetSupportedLanguagesResponse\"\x00\x12_\n\x14GetSupportedSpeakers\x12!.rime.GetSupportedSpeakersRequest\x1a\".rime.GetSupportedSpeakersResponse\"\x00\x62\x06proto3')
+
+_globals = globals()
+_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
+_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'rime_api.text_to_speech_pb2', _globals)
+if not _descriptor._USE_C_DESCRIPTORS:
+  DESCRIPTOR._loaded_options = None
+  _globals['_SPLITSTRATEGY']._serialized_start=3281
+  _globals['_SPLITSTRATEGY']._serialized_end=3422
+  _globals['_STREAMINGSYNTHESISREQUEST']._serialized_start=96
+  _globals['_STREAMINGSYNTHESISREQUEST']._serialized_end=211
+  _globals['_SYNTHESISREQUEST']._serialized_start=214
+  _globals['_SYNTHESISREQUEST']._serialized_end=749
+  _globals['_PRONUNCIATIONENTRY']._serialized_start=751
+  _globals['_PRONUNCIATIONENTRY']._serialized_end=812
+  _globals['_SYNTHESISRESPONSESTREAM']._serialized_start=814
+  _globals['_SYNTHESISRESPONSESTREAM']._serialized_end=918
+  _globals['_SYNTHESISRESPONSETRAILER']._serialized_start=920
+  _globals['_SYNTHESISRESPONSETRAILER']._serialized_end=1004
+  _globals['_AUDIOPARAMETERS']._serialized_start=1007
+  _globals['_AUDIOPARAMETERS']._serialized_end=1168
+  _globals['_CODAPARAMETERS']._serialized_start=1171
+  _globals['_CODAPARAMETERS']._serialized_end=1368
+  _globals['_MISTPARAMETERS']._serialized_start=1371
+  _globals['_MISTPARAMETERS']._serialized_end=1596
+  _globals['_TIMESTAMPOPTIONS']._serialized_start=1598
+  _globals['_TIMESTAMPOPTIONS']._serialized_end=1632
+  _globals['_SPANTIMESTAMP']._serialized_start=1634
+  _globals['_SPANTIMESTAMP']._serialized_end=1745
+  _globals['_TIMESTAMPS']._serialized_start=1747
+  _globals['_TIMESTAMPS']._serialized_end=1831
+  _globals['_NORMALIZETEXTREQUEST']._serialized_start=1833
+  _globals['_NORMALIZETEXTREQUEST']._serialized_end=1955
+  _globals['_NORMALIZETEXTRESPONSE']._serialized_start=1957
+  _globals['_NORMALIZETEXTRESPONSE']._serialized_end=2035
+  _globals['_GETSUPPORTEDLANGUAGESREQUEST']._serialized_start=2037
+  _globals['_GETSUPPORTEDLANGUAGESREQUEST']._serialized_end=2067
+  _globals['_GETSUPPORTEDLANGUAGESRESPONSE']._serialized_start=2069
+  _globals['_GETSUPPORTEDLANGUAGESRESPONSE']._serialized_end=2119
+  _globals['_GETSUPPORTEDSPEAKERSREQUEST']._serialized_start=2121
+  _globals['_GETSUPPORTEDSPEAKERSREQUEST']._serialized_end=2186
+  _globals['_GETSUPPORTEDSPEAKERSRESPONSE']._serialized_start=2188
+  _globals['_GETSUPPORTEDSPEAKERSRESPONSE']._serialized_end=2236
+  _globals['_WEBSOCKETREQUEST']._serialized_start=2239
+  _globals['_WEBSOCKETREQUEST']._serialized_end=2475
+  _globals['_WEBSOCKETCONFIG']._serialized_start=2478
+  _globals['_WEBSOCKETCONFIG']._serialized_end=2635
+  _globals['_WEBSOCKETEND']._serialized_start=2637
+  _globals['_WEBSOCKETEND']._serialized_end=2651
+  _globals['_WEBSOCKETCANCEL']._serialized_start=2653
+  _globals['_WEBSOCKETCANCEL']._serialized_end=2670
+  _globals['_WEBSOCKETRESPONSE']._serialized_start=2673
+  _globals['_WEBSOCKETRESPONSE']._serialized_end=2945
+  _globals['_WEBSOCKETREADY']._serialized_start=2947
+  _globals['_WEBSOCKETREADY']._serialized_end=3052
+  _globals['_WEBSOCKETSTARTED']._serialized_start=3054
+  _globals['_WEBSOCKETSTARTED']._serialized_end=3092
+  _globals['_WEBSOCKETDONE']._serialized_start=3094
+  _globals['_WEBSOCKETDONE']._serialized_end=3167
+  _globals['_WEBSOCKETCANCELLED']._serialized_start=3169
+  _globals['_WEBSOCKETCANCELLED']._serialized_end=3189
+  _globals['_WEBSOCKETERROR']._serialized_start=3191
+  _globals['_WEBSOCKETERROR']._serialized_end=3278
+  _globals['_TEXTTOSPEECH']._serialized_start=3425
+  _globals['_TEXTTOSPEECH']._serialized_end=3878
+# @@protoc_insertion_point(module_scope)

{rime_api-0.2.0 → rime_api-0.3.0}/src/rime_api/text_to_speech_pb2.pyi

@@ -28,7 +28,7 @@ class StreamingSynthesisRequest(_message.Message):
     def __init__(self, header: _Optional[_Union[SynthesisRequest, _Mapping]] = ..., text_chunk: _Optional[str] = ...) -> None: ...
 
 class SynthesisRequest(_message.Message):
-    __slots__ = ("language", "speaker", "text", "audio_parameters", "split_strategy", "coda_parameters", "mist_parameters", "timestamps")
+    __slots__ = ("language", "speaker", "text", "audio_parameters", "split_strategy", "coda_parameters", "mist_parameters", "timestamps", "custom_lexicon")
     LANGUAGE_FIELD_NUMBER: _ClassVar[int]
     SPEAKER_FIELD_NUMBER: _ClassVar[int]
     TEXT_FIELD_NUMBER: _ClassVar[int]
@@ -37,6 +37,7 @@ class SynthesisRequest(_message.Message):
     CODA_PARAMETERS_FIELD_NUMBER: _ClassVar[int]
     MIST_PARAMETERS_FIELD_NUMBER: _ClassVar[int]
     TIMESTAMPS_FIELD_NUMBER: _ClassVar[int]
+    CUSTOM_LEXICON_FIELD_NUMBER: _ClassVar[int]
     language: str
     speaker: str
     text: str
@@ -45,7 +46,16 @@ class SynthesisRequest(_message.Message):
     coda_parameters: CodaParameters
     mist_parameters: MistParameters
     timestamps: TimestampOptions
-    def __init__(self, language: _Optional[str] = ..., speaker: _Optional[str] = ..., text: _Optional[str] = ..., audio_parameters: _Optional[_Union[AudioParameters, _Mapping]] = ..., split_strategy: _Optional[_Union[SplitStrategy, str]] = ..., coda_parameters: _Optional[_Union[CodaParameters, _Mapping]] = ..., mist_parameters: _Optional[_Union[MistParameters, _Mapping]] = ..., timestamps: _Optional[_Union[TimestampOptions, _Mapping]] = ...) -> None: ...
+    custom_lexicon: _containers.RepeatedCompositeFieldContainer[PronunciationEntry]
+    def __init__(self, language: _Optional[str] = ..., speaker: _Optional[str] = ..., text: _Optional[str] = ..., audio_parameters: _Optional[_Union[AudioParameters, _Mapping]] = ..., split_strategy: _Optional[_Union[SplitStrategy, str]] = ..., coda_parameters: _Optional[_Union[CodaParameters, _Mapping]] = ..., mist_parameters: _Optional[_Union[MistParameters, _Mapping]] = ..., timestamps: _Optional[_Union[TimestampOptions, _Mapping]] = ..., custom_lexicon: _Optional[_Iterable[_Union[PronunciationEntry, _Mapping]]] = ...) -> None: ...
+
+class PronunciationEntry(_message.Message):
+    __slots__ = ("spelling", "pronunciation")
+    SPELLING_FIELD_NUMBER: _ClassVar[int]
+    PRONUNCIATION_FIELD_NUMBER: _ClassVar[int]
+    spelling: str
+    pronunciation: str
+    def __init__(self, spelling: _Optional[str] = ..., pronunciation: _Optional[str] = ...) -> None: ...
 
 class SynthesisResponseStream(_message.Message):
     __slots__ = ("audio", "trailer")
@@ -114,12 +124,14 @@ class Timestamps(_message.Message):
     def __init__(self, status: _Optional[_Union[_status_pb2.Status, _Mapping]] = ..., spans: _Optional[_Iterable[_Union[SpanTimestamp, _Mapping]]] = ...) -> None: ...
 
 class NormalizeTextRequest(_message.Message):
-    __slots__ = ("text", "language")
+    __slots__ = ("text", "language", "custom_lexicon")
     TEXT_FIELD_NUMBER: _ClassVar[int]
     LANGUAGE_FIELD_NUMBER: _ClassVar[int]
+    CUSTOM_LEXICON_FIELD_NUMBER: _ClassVar[int]
     text: str
     language: str
-    def __init__(self, text: _Optional[str] = ..., language: _Optional[str] = ...) -> None: ...
+    custom_lexicon: _containers.RepeatedCompositeFieldContainer[PronunciationEntry]
+    def __init__(self, text: _Optional[str] = ..., language: _Optional[str] = ..., custom_lexicon: _Optional[_Iterable[_Union[PronunciationEntry, _Mapping]]] = ...) -> None: ...
 
 class NormalizeTextResponse(_message.Message):
     __slots__ = ("normalized_text", "normalized_sentences")

rime_api-0.2.0/src/rime_api/text_to_speech_pb2.py

@@ -1,92 +0,0 @@
-# -*- coding: utf-8 -*-
-# Generated by the protocol buffer compiler.  DO NOT EDIT!
-# NO CHECKED-IN PROTOBUF GENCODE
-# source: rime_api/text_to_speech.proto
-# Protobuf Python Version: 5.29.0
-"""Generated protocol buffer code."""
-from google.protobuf import descriptor as _descriptor
-from google.protobuf import descriptor_pool as _descriptor_pool
-from google.protobuf import runtime_version as _runtime_version
-from google.protobuf import symbol_database as _symbol_database
-from google.protobuf.internal import builder as _builder
-_runtime_version.ValidateProtobufRuntimeVersion(
-    _runtime_version.Domain.PUBLIC,
-    5,
-    29,
-    0,
-    '',
-    'rime_api/text_to_speech.proto'
-)
-# @@protoc_insertion_point(imports)
-
-_sym_db = _symbol_database.Default()
-
-
-from google.protobuf import duration_pb2 as google_dot_protobuf_dot_duration__pb2
-from google.rpc import status_pb2 as google_dot_rpc_dot_status__pb2
-
-
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\x1drime_api/text_to_speech.proto\x12\x04rime\x1a\x1egoogle/protobuf/duration.proto\x1a\x17google/rpc/status.proto\"s\n\x19StreamingSynthesisRequest\x12(\n\x06header\x18\x01 \x01(\x0b\x32\x16.rime.SynthesisRequestH\x00\x12\x14\n\ntext_chunk\x18\x02 \x01(\tH\x00\x42\t\n\x07payloadJ\x04\x08\x03\x10\x04R\x05\x66lush\"\xe5\x03\n\x10SynthesisRequest\x12\x15\n\x08language\x18\x02 \x01(\tH\x00\x88\x01\x01\x12\x14\n\x07speaker\x18\x03 \x01(\tH\x01\x88\x01\x01\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x34\n\x10\x61udio_parameters\x18\x05 \x01(\x0b\x32\x15.rime.AudioParametersH\x02\x88\x01\x01\x12\x30\n\x0esplit_strategy\x18\x06 \x01(\x0e\x32\x13.rime.SplitStrategyH\x03\x88\x01\x01\x12\x32\n\x0f\x63oda_parameters\x18\x08 \x01(\x0b\x32\x14.rime.CodaParametersH\x04\x88\x01\x01\x12\x32\n\x0fmist_parameters\x18\t \x01(\x0b\x32\x14.rime.MistParametersH\x05\x88\x01\x01\x12/\n\ntimestamps\x18\n \x01(\x0b\x32\x16.rime.TimestampOptionsH\x06\x88\x01\x01\x42\x0b\n\t_languageB\n\n\x08_speakerB\x13\n\x11_audio_parametersB\x11\n\x0f_split_strategyB\x12\n\x10_coda_parametersB\x12\n\x10_mist_parametersB\r\n\x0b_timestampsJ\x04\x08\x01\x10\x02J\x04\x08\x07\x10\x08R\x11\x61rcana_parameters\"h\n\x17SynthesisResponseStream\x12\x0f\n\x05\x61udio\x18\x01 \x01(\x0cH\x00\x12\x31\n\x07trailer\x18\x02 \x01(\x0b\x32\x1e.rime.SynthesisResponseTrailerH\x00\x42\t\n\x07payload\"T\n\x18SynthesisResponseTrailer\x12)\n\ntimestamps\x18\x01 \x01(\x0b\x32\x10.rime.TimestampsH\x00\x88\x01\x01\x42\r\n\x0b_timestamps\"\xa1\x01\n\x0f\x41udioParameters\x12\x19\n\x0c\x61udio_format\x18\x01 \x01(\tH\x00\x88\x01\x01\x12\x1a\n\rsampling_rate\x18\x02 \x01(\x05H\x01\x88\x01\x01\x12\x1e\n\x11time_scale_factor\x18\x03 \x01(\x02H\x02\x88\x01\x01\x42\x0f\n\r_audio_formatB\x10\n\x0e_sampling_rateB\x14\n\x12_time_scale_factor\"\xc5\x01\n\x0e\x43odaParameters\x12\"\n\x15text_lookahead_tokens\x18\x08 \x01(\x05H\x00\x88\x01\x01\x42\x18\n\x16_text_lookahead_tokensJ\x04\x08\x01\x10\x02J\x04\x08\x02\x10\x03J\x04\x08\x03\x10\x04J\x04\x08\x04\x10\x05J\x04\x08\x05\x10\x06J\x04\x08\x06\x10\x07J\x04\x08\x07\x10\x08R\x0btemperatureR\x05top_kR\x05top_pR\x12repetition_penaltyR\nmax_tokensR\nmin_tokensR\x04seed\"\xe1\x01\n\x0eMistParameters\x12#\n\x16pause_between_brackets\x18\x01 \x01(\x08H\x00\x88\x01\x01\x12\'\n\x1aphonemize_between_brackets\x18\x02 \x01(\x08H\x01\x88\x01\x01\x12!\n\x19inline_time_scale_factors\x18\x03 \x03(\x02\x12\x16\n\tsave_oovs\x18\x04 \x01(\x08H\x02\x88\x01\x01\x42\x19\n\x17_pause_between_bracketsB\x1d\n\x1b_phonemize_between_bracketsB\x0c\n\n_save_oovs\"\"\n\x10TimestampOptions\x12\x0e\n\x06\x65nable\x18\x01 \x01(\x08\"o\n\rSpanTimestamp\x12\x0c\n\x04text\x18\x01 \x01(\t\x12(\n\x05start\x18\x02 \x01(\x0b\x32\x19.google.protobuf.Duration\x12&\n\x03\x65nd\x18\x03 \x01(\x0b\x32\x19.google.protobuf.Duration\"T\n\nTimestamps\x12\"\n\x06status\x18\x01 \x01(\x0b\x32\x12.google.rpc.Status\x12\"\n\x05spans\x18\x02 \x03(\x0b\x32\x13.rime.SpanTimestamp\"H\n\x14NormalizeTextRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\x15\n\x08language\x18\x02 \x01(\tH\x00\x88\x01\x01\x42\x0b\n\t_language\"N\n\x15NormalizeTextResponse\x12\x17\n\x0fnormalized_text\x18\x01 \x01(\t\x12\x1c\n\x14normalized_sentences\x18\x02 \x03(\t\"\x1e\n\x1cGetSupportedLanguagesRequest\"2\n\x1dGetSupportedLanguagesResponse\x12\x11\n\tlanguages\x18\x01 \x03(\t\"A\n\x1bGetSupportedSpeakersRequest\x12\x15\n\x08language\x18\x01 \x01(\tH\x00\x88\x01\x01\x42\x0b\n\t_language\"0\n\x1cGetSupportedSpeakersResponse\x12\x10\n\x08speakers\x18\x01 \x03(\t\"\xec\x01\n\x10WebSocketRequest\x12\x12\n\ncontext_id\x18\x01 \x01(\t\x12\'\n\x06\x63onfig\x18\x02 \x01(\x0b\x32\x15.rime.WebSocketConfigH\x00\x12\'\n\x05start\x18\x03 \x01(\x0b\x32\x16.rime.SynthesisRequestH\x00\x12\x0e\n\x04text\x18\x04 \x01(\tH\x00\x12!\n\x03\x65nd\x18\x05 \x01(\x0b\x32\x12.rime.WebSocketEndH\x00\x12\'\n\x06\x63\x61ncel\x18\x06 \x01(\x0b\x32\x15.rime.WebSocketCancelH\x00\x42\t\n\x07payloadJ\x04\x08\x07\x10\x08R\x05\x66lush\"\x9d\x01\n\x0fWebSocketConfig\x12\x1a\n\rauthorization\x18\x01 \x01(\tH\x00\x88\x01\x01\x12\x14\n\x07license\x18\x02 \x01(\tH\x01\x88\x01\x01\x12-\n\x08\x64\x65\x66\x61ults\x18\x03 \x01(\x0b\x32\x16.rime.SynthesisRequestH\x02\x88\x01\x01\x42\x10\n\x0e_authorizationB\n\n\x08_licenseB\x0b\n\t_defaults\"\x0e\n\x0cWebSocketEnd\"\x11\n\x0fWebSocketCancel\"\x90\x02\n\x11WebSocketResponse\x12\x12\n\ncontext_id\x18\x01 \x01(\t\x12%\n\x05ready\x18\x02 \x01(\x0b\x32\x14.rime.WebSocketReadyH\x00\x12)\n\x07started\x18\x03 \x01(\x0b\x32\x16.rime.WebSocketStartedH\x00\x12\x0f\n\x05\x61udio\x18\x04 \x01(\x0cH\x00\x12#\n\x04\x64one\x18\x05 \x01(\x0b\x32\x13.rime.WebSocketDoneH\x00\x12-\n\tcancelled\x18\x06 \x01(\x0b\x32\x18.rime.WebSocketCancelledH\x00\x12%\n\x05\x65rror\x18\x07 \x01(\x0b\x32\x14.rime.WebSocketErrorH\x00\x42\t\n\x07payload\"i\n\x0eWebSocketReady\x12\x10\n\x08protocol\x18\x01 \x01(\r\x12\x11\n\tlanguages\x18\x02 \x03(\t\x12\x1d\n\x10\x64\x65\x66\x61ult_language\x18\x03 \x01(\tH\x00\x88\x01\x01\x42\x13\n\x11_default_language\"&\n\x10WebSocketStarted\x12\x12\n\nrequest_id\x18\x01 \x01(\t\"I\n\rWebSocketDone\x12)\n\ntimestamps\x18\x01 \x01(\x0b\x32\x10.rime.TimestampsH\x00\x88\x01\x01\x42\r\n\x0b_timestamps\"\x14\n\x12WebSocketCancelled\"W\n\x0eWebSocketError\x12\x0c\n\x04kind\x18\x01 \x01(\t\x12\x0f\n\x07message\x18\x02 \x01(\t\x12\x17\n\nrequest_id\x18\x03 \x01(\tH\x00\x88\x01\x01\x42\r\n\x0b_request_id*\x8d\x01\n\rSplitStrategy\x12\x1e\n\x1aSPLIT_STRATEGY_UNSPECIFIED\x10\x00\x12\x1b\n\x17SPLIT_STRATEGY_SENTENCE\x10\x01\x12\x17\n\x13SPLIT_STRATEGY_NONE\x10\x02\x12&\n\"SPLIT_STRATEGY_ACCUMULATE_SENTENCE\x10\x03\x32\xc5\x03\n\x0cTextToSpeech\x12G\n\nSynthesize\x12\x16.rime.SynthesisRequest\x1a\x1d.rime.SynthesisResponseStream\"\x00\x30\x01\x12[\n\x13SynthesizeStreaming\x12\x1f.rime.StreamingSynthesisRequest\x1a\x1d.rime.SynthesisResponseStream\"\x00(\x01\x30\x01\x12J\n\rNormalizeText\x12\x1a.rime.NormalizeTextRequest\x1a\x1b.rime.NormalizeTextResponse\"\x00\x12\x62\n\x15GetSupportedLanguages\x12\".rime.GetSupportedLanguagesRequest\x1a#.rime.GetSupportedLanguagesResponse\"\x00\x12_\n\x14GetSupportedSpeakers\x12!.rime.GetSupportedSpeakersRequest\x1a\".rime.GetSupportedSpeakersResponse\"\x00\x62\x06proto3')
-
-_globals = globals()
-_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
-_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'rime_api.text_to_speech_pb2', _globals)
-if not _descriptor._USE_C_DESCRIPTORS:
-  DESCRIPTOR._loaded_options = None
-  _globals['_SPLITSTRATEGY']._serialized_start=3118
-  _globals['_SPLITSTRATEGY']._serialized_end=3259
-  _globals['_STREAMINGSYNTHESISREQUEST']._serialized_start=96
-  _globals['_STREAMINGSYNTHESISREQUEST']._serialized_end=211
-  _globals['_SYNTHESISREQUEST']._serialized_start=214
-  _globals['_SYNTHESISREQUEST']._serialized_end=699
-  _globals['_SYNTHESISRESPONSESTREAM']._serialized_start=701
-  _globals['_SYNTHESISRESPONSESTREAM']._serialized_end=805
-  _globals['_SYNTHESISRESPONSETRAILER']._serialized_start=807
-  _globals['_SYNTHESISRESPONSETRAILER']._serialized_end=891
-  _globals['_AUDIOPARAMETERS']._serialized_start=894
-  _globals['_AUDIOPARAMETERS']._serialized_end=1055
-  _globals['_CODAPARAMETERS']._serialized_start=1058
-  _globals['_CODAPARAMETERS']._serialized_end=1255
-  _globals['_MISTPARAMETERS']._serialized_start=1258
-  _globals['_MISTPARAMETERS']._serialized_end=1483
-  _globals['_TIMESTAMPOPTIONS']._serialized_start=1485
-  _globals['_TIMESTAMPOPTIONS']._serialized_end=1519
-  _globals['_SPANTIMESTAMP']._serialized_start=1521
-  _globals['_SPANTIMESTAMP']._serialized_end=1632
-  _globals['_TIMESTAMPS']._serialized_start=1634
-  _globals['_TIMESTAMPS']._serialized_end=1718
-  _globals['_NORMALIZETEXTREQUEST']._serialized_start=1720
-  _globals['_NORMALIZETEXTREQUEST']._serialized_end=1792
-  _globals['_NORMALIZETEXTRESPONSE']._serialized_start=1794
-  _globals['_NORMALIZETEXTRESPONSE']._serialized_end=1872
-  _globals['_GETSUPPORTEDLANGUAGESREQUEST']._serialized_start=1874
-  _globals['_GETSUPPORTEDLANGUAGESREQUEST']._serialized_end=1904
-  _globals['_GETSUPPORTEDLANGUAGESRESPONSE']._serialized_start=1906
-  _globals['_GETSUPPORTEDLANGUAGESRESPONSE']._serialized_end=1956
-  _globals['_GETSUPPORTEDSPEAKERSREQUEST']._serialized_start=1958
-  _globals['_GETSUPPORTEDSPEAKERSREQUEST']._serialized_end=2023
-  _globals['_GETSUPPORTEDSPEAKERSRESPONSE']._serialized_start=2025
-  _globals['_GETSUPPORTEDSPEAKERSRESPONSE']._serialized_end=2073
-  _globals['_WEBSOCKETREQUEST']._serialized_start=2076
-  _globals['_WEBSOCKETREQUEST']._serialized_end=2312
-  _globals['_WEBSOCKETCONFIG']._serialized_start=2315
-  _globals['_WEBSOCKETCONFIG']._serialized_end=2472
-  _globals['_WEBSOCKETEND']._serialized_start=2474
-  _globals['_WEBSOCKETEND']._serialized_end=2488
-  _globals['_WEBSOCKETCANCEL']._serialized_start=2490
-  _globals['_WEBSOCKETCANCEL']._serialized_end=2507
-  _globals['_WEBSOCKETRESPONSE']._serialized_start=2510
-  _globals['_WEBSOCKETRESPONSE']._serialized_end=2782
-  _globals['_WEBSOCKETREADY']._serialized_start=2784
-  _globals['_WEBSOCKETREADY']._serialized_end=2889
-  _globals['_WEBSOCKETSTARTED']._serialized_start=2891
-  _globals['_WEBSOCKETSTARTED']._serialized_end=2929
-  _globals['_WEBSOCKETDONE']._serialized_start=2931
-  _globals['_WEBSOCKETDONE']._serialized_end=3004
-  _globals['_WEBSOCKETCANCELLED']._serialized_start=3006
-  _globals['_WEBSOCKETCANCELLED']._serialized_end=3026
-  _globals['_WEBSOCKETERROR']._serialized_start=3028
-  _globals['_WEBSOCKETERROR']._serialized_end=3115
-  _globals['_TEXTTOSPEECH']._serialized_start=3262
-  _globals['_TEXTTOSPEECH']._serialized_end=3715
-# @@protoc_insertion_point(module_scope)