1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340
// This file is @generated by prost-build.
/// Provides information to the speech translation that specifies how to process
/// the request.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TranslateSpeechConfig {
/// Required. Encoding of audio data.
/// Supported formats:
///
/// - `linear16`
///
/// Uncompressed 16-bit signed little-endian samples (Linear PCM).
///
/// - `flac`
///
/// `flac` (Free Lossless Audio Codec) is the recommended encoding
/// because it is lossless--therefore recognition is not compromised--and
/// requires only about half the bandwidth of `linear16`.
///
/// - `mulaw`
///
/// 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
///
/// - `amr`
///
/// Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.
///
/// - `amr-wb`
///
/// Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.
///
/// - `ogg-opus`
///
/// Opus encoded audio frames in [Ogg](<https://wikipedia.org/wiki/Ogg>)
/// container. `sample_rate_hertz` must be one of 8000, 12000, 16000, 24000,
/// or 48000.
///
/// - `mp3`
///
/// MP3 audio. Support all standard MP3 bitrates (which range from 32-320
/// kbps). When using this encoding, `sample_rate_hertz` has to match the
/// sample rate of the file being used.
#[prost(string, tag = "1")]
pub audio_encoding: ::prost::alloc::string::String,
/// Required. Source language code (BCP-47) of the input audio.
#[prost(string, tag = "2")]
pub source_language_code: ::prost::alloc::string::String,
/// Required. Target language code (BCP-47) of the output.
#[prost(string, tag = "3")]
pub target_language_code: ::prost::alloc::string::String,
/// Optional. Sample rate in Hertz of the audio data. Valid values are:
/// 8000-48000. 16000 is optimal. For best results, set the sampling rate of
/// the audio source to 16000 Hz. If that's not possible, use the native sample
/// rate of the audio source (instead of re-sampling).
#[prost(int32, tag = "4")]
pub sample_rate_hertz: i32,
/// Optional. `google-provided-model/video` and
/// `google-provided-model/enhanced-phone-call` are premium models.
/// `google-provided-model/phone-call` is not premium model.
#[prost(string, tag = "5")]
pub model: ::prost::alloc::string::String,
}
/// Config used for streaming translation.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct StreamingTranslateSpeechConfig {
/// Required. The common config for all the following audio contents.
#[prost(message, optional, tag = "1")]
pub audio_config: ::core::option::Option<TranslateSpeechConfig>,
/// Optional. If `false` or omitted, the system performs
/// continuous translation (continuing to wait for and process audio even if
/// the user pauses speaking) until the client closes the input stream (gRPC
/// API) or until the maximum time limit has been reached. May return multiple
/// `StreamingTranslateSpeechResult`s with the `is_final` flag set to `true`.
///
/// If `true`, the speech translator will detect a single spoken utterance.
/// When it detects that the user has paused or stopped speaking, it will
/// return an `END_OF_SINGLE_UTTERANCE` event and cease translation.
/// When the client receives 'END_OF_SINGLE_UTTERANCE' event, the client should
/// stop sending the requests. However, clients should keep receiving remaining
/// responses until the stream is terminated. To construct the complete
/// sentence in a streaming way, one should override (if 'is_final' of previous
/// response is false), or append (if 'is_final' of previous response is true).
#[prost(bool, tag = "2")]
pub single_utterance: bool,
}
/// The top-level message sent by the client for the `StreamingTranslateSpeech`
/// method. Multiple `StreamingTranslateSpeechRequest` messages are sent. The
/// first message must contain a `streaming_config` message and must not contain
/// `audio_content` data. All subsequent messages must contain `audio_content`
/// data and must not contain a `streaming_config` message.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct StreamingTranslateSpeechRequest {
/// The streaming request, which is either a streaming config or content.
#[prost(
oneof = "streaming_translate_speech_request::StreamingRequest",
tags = "1, 2"
)]
pub streaming_request: ::core::option::Option<
streaming_translate_speech_request::StreamingRequest,
>,
}
/// Nested message and enum types in `StreamingTranslateSpeechRequest`.
pub mod streaming_translate_speech_request {
/// The streaming request, which is either a streaming config or content.
#[derive(Clone, PartialEq, ::prost::Oneof)]
pub enum StreamingRequest {
/// Provides information to the recognizer that specifies how to process the
/// request. The first `StreamingTranslateSpeechRequest` message must contain
/// a `streaming_config` message.
#[prost(message, tag = "1")]
StreamingConfig(super::StreamingTranslateSpeechConfig),
/// The audio data to be translated. Sequential chunks of audio data are sent
/// in sequential `StreamingTranslateSpeechRequest` messages. The first
/// `StreamingTranslateSpeechRequest` message must not contain
/// `audio_content` data and all subsequent `StreamingTranslateSpeechRequest`
/// messages must contain `audio_content` data. The audio bytes must be
/// encoded as specified in `StreamingTranslateSpeechConfig`. Note: as with
/// all bytes fields, protobuffers use a pure binary representation (not
/// base64).
#[prost(bytes, tag = "2")]
AudioContent(::prost::bytes::Bytes),
}
}
/// A streaming speech translation result corresponding to a portion of the audio
/// that is currently being processed.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct StreamingTranslateSpeechResult {
/// Translation result.
#[prost(oneof = "streaming_translate_speech_result::Result", tags = "1")]
pub result: ::core::option::Option<streaming_translate_speech_result::Result>,
}
/// Nested message and enum types in `StreamingTranslateSpeechResult`.
pub mod streaming_translate_speech_result {
/// Text translation result.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TextTranslationResult {
/// Output only. The translated sentence.
#[prost(string, tag = "1")]
pub translation: ::prost::alloc::string::String,
/// Output only. If `false`, this `StreamingTranslateSpeechResult` represents
/// an interim result that may change. If `true`, this is the final time the
/// translation service will return this particular
/// `StreamingTranslateSpeechResult`, the streaming translator will not
/// return any further hypotheses for this portion of the transcript and
/// corresponding audio.
#[prost(bool, tag = "2")]
pub is_final: bool,
}
/// Translation result.
#[derive(Clone, PartialEq, ::prost::Oneof)]
pub enum Result {
/// Text translation result.
#[prost(message, tag = "1")]
TextTranslationResult(TextTranslationResult),
}
}
/// A streaming speech translation response corresponding to a portion of
/// the audio currently processed.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct StreamingTranslateSpeechResponse {
/// Output only. If set, returns a [google.rpc.Status][google.rpc.Status] message that
/// specifies the error for the operation.
#[prost(message, optional, tag = "1")]
pub error: ::core::option::Option<super::super::super::rpc::Status>,
/// Output only. The translation result that is currently being processed (is_final could be
/// true or false).
#[prost(message, optional, tag = "2")]
pub result: ::core::option::Option<StreamingTranslateSpeechResult>,
/// Output only. Indicates the type of speech event.
#[prost(
enumeration = "streaming_translate_speech_response::SpeechEventType",
tag = "3"
)]
pub speech_event_type: i32,
}
/// Nested message and enum types in `StreamingTranslateSpeechResponse`.
pub mod streaming_translate_speech_response {
/// Indicates the type of speech event.
#[derive(
Clone,
Copy,
Debug,
PartialEq,
Eq,
Hash,
PartialOrd,
Ord,
::prost::Enumeration
)]
#[repr(i32)]
pub enum SpeechEventType {
/// No speech event specified.
Unspecified = 0,
/// This event indicates that the server has detected the end of the user's
/// speech utterance and expects no additional speech. Therefore, the server
/// will not process additional audio (although it may subsequently return
/// additional results). When the client receives 'END_OF_SINGLE_UTTERANCE'
/// event, the client should stop sending the requests. However, clients
/// should keep receiving remaining responses until the stream is terminated.
/// To construct the complete sentence in a streaming way, one should
/// override (if 'is_final' of previous response is false), or append (if
/// 'is_final' of previous response is true). This event is only sent if
/// `single_utterance` was set to `true`, and is not used otherwise.
EndOfSingleUtterance = 1,
}
impl SpeechEventType {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
SpeechEventType::Unspecified => "SPEECH_EVENT_TYPE_UNSPECIFIED",
SpeechEventType::EndOfSingleUtterance => "END_OF_SINGLE_UTTERANCE",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"SPEECH_EVENT_TYPE_UNSPECIFIED" => Some(Self::Unspecified),
"END_OF_SINGLE_UTTERANCE" => Some(Self::EndOfSingleUtterance),
_ => None,
}
}
}
}
/// Generated client implementations.
pub mod speech_translation_service_client {
#![allow(unused_variables, dead_code, missing_docs, clippy::let_unit_value)]
use tonic::codegen::*;
use tonic::codegen::http::Uri;
/// Provides translation from/to media types.
#[derive(Debug, Clone)]
pub struct SpeechTranslationServiceClient<T> {
inner: tonic::client::Grpc<T>,
}
impl<T> SpeechTranslationServiceClient<T>
where
T: tonic::client::GrpcService<tonic::body::BoxBody>,
T::Error: Into<StdError>,
T::ResponseBody: Body<Data = Bytes> + std::marker::Send + 'static,
<T::ResponseBody as Body>::Error: Into<StdError> + std::marker::Send,
{
pub fn new(inner: T) -> Self {
let inner = tonic::client::Grpc::new(inner);
Self { inner }
}
pub fn with_origin(inner: T, origin: Uri) -> Self {
let inner = tonic::client::Grpc::with_origin(inner, origin);
Self { inner }
}
pub fn with_interceptor<F>(
inner: T,
interceptor: F,
) -> SpeechTranslationServiceClient<InterceptedService<T, F>>
where
F: tonic::service::Interceptor,
T::ResponseBody: Default,
T: tonic::codegen::Service<
http::Request<tonic::body::BoxBody>,
Response = http::Response<
<T as tonic::client::GrpcService<tonic::body::BoxBody>>::ResponseBody,
>,
>,
<T as tonic::codegen::Service<
http::Request<tonic::body::BoxBody>,
>>::Error: Into<StdError> + std::marker::Send + std::marker::Sync,
{
SpeechTranslationServiceClient::new(
InterceptedService::new(inner, interceptor),
)
}
/// Compress requests with the given encoding.
///
/// This requires the server to support it otherwise it might respond with an
/// error.
#[must_use]
pub fn send_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.send_compressed(encoding);
self
}
/// Enable decompressing responses.
#[must_use]
pub fn accept_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.accept_compressed(encoding);
self
}
/// Limits the maximum size of a decoded message.
///
/// Default: `4MB`
#[must_use]
pub fn max_decoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_decoding_message_size(limit);
self
}
/// Limits the maximum size of an encoded message.
///
/// Default: `usize::MAX`
#[must_use]
pub fn max_encoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_encoding_message_size(limit);
self
}
/// Performs bidirectional streaming speech translation: receive results while
/// sending audio. This method is only available via the gRPC API (not REST).
pub async fn streaming_translate_speech(
&mut self,
request: impl tonic::IntoStreamingRequest<
Message = super::StreamingTranslateSpeechRequest,
>,
) -> std::result::Result<
tonic::Response<
tonic::codec::Streaming<super::StreamingTranslateSpeechResponse>,
>,
tonic::Status,
> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.mediatranslation.v1beta1.SpeechTranslationService/StreamingTranslateSpeech",
);
let mut req = request.into_streaming_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.mediatranslation.v1beta1.SpeechTranslationService",
"StreamingTranslateSpeech",
),
);
self.inner.streaming(req, path, codec).await
}
}
}