Chiebot-Mirror
/
googleapis
8
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update to speech.

Browse Source
pull/175/head
landrito 9 years ago
parent 65eaa0ef19
commit 07d1887d6d
1 changed files with 105 additions and 26 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 131
      google/cloud/speech/v1beta1/cloud_speech.proto

131
google/cloud/speech/v1beta1/cloud_speech.proto
Unescape View File

@ -18,6 +18,7 @@ package google.cloud.speech.v1beta1;
import "google/api/annotations.proto";
import "google/longrunning/operations.proto";
import "google/protobuf/timestamp.proto";
import "google/rpc/status.proto";
option java_multiple_files = true;
@ -34,8 +35,9 @@ service Speech {
}
// Perform asynchronous speech-recognition: receive results via the
// google.longrunning.Operations interface. `Operation.response` returns
// `AsyncRecognizeResponse`.
// google.longrunning.Operations interface. Returns either an
// `Operation.error` or an `Operation.response` which contains
// an `AsyncRecognizeResponse` message.
rpc AsyncRecognize(AsyncRecognizeRequest) returns (google.longrunning.Operation) {
option (google.api.http) = { post: "/v1beta1/speech:asyncrecognize" body: "*" };
}
@ -87,7 +89,8 @@ message StreamingRecognizeRequest {
// and all subsequent `StreamingRecognizeRequest` messages must contain
// `audio_content` data. The audio bytes must be encoded as specified in
// `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
// pure binary representation (not base64).
// pure binary representation (not base64). See
// [audio limits](https://cloud.google.com/speech/limits#content).
bytes audio_content = 2;
}
}
@ -102,13 +105,13 @@ message StreamingRecognitionConfig {
// [Optional] If `false` or omitted, the recognizer will perform continuous
// recognition (continuing to process audio even if the user pauses speaking)
// until the client closes the output stream (gRPC API) or when the maximum
// time limit has been reached. Multiple `SpeechRecognitionResult`s with the
// `is_final` flag set to `true` may be returned.
// time limit has been reached. Multiple `StreamingRecognitionResult`s with
// the `is_final` flag set to `true` may be returned.
//
// If `true`, the recognizer will detect a single spoken utterance. When it
// detects that the user has paused or stopped speaking, it will return an
// `END_OF_UTTERANCE` event and cease recognition. It will return no more than
// one `SpeechRecognitionResult` with the `is_final` flag set to `true`.
// one `StreamingRecognitionResult` with the `is_final` flag set to `true`.
bool single_utterance = 2;
// [Optional] If `true`, interim results (tentative hypotheses) may be
@ -134,7 +137,7 @@ message RecognitionConfig {
// Not specified. Will return result [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
ENCODING_UNSPECIFIED = 0;
// Uncompressed 16-bit signed little-endian samples.
// Uncompressed 16-bit signed little-endian samples (Linear PCM).
// This is the only encoding that may be used by `AsyncRecognize`.
LINEAR16 = 1;
@ -144,7 +147,7 @@ message RecognitionConfig {
//
// The stream FLAC (Free Lossless Audio Codec) encoding is specified at:
// http://flac.sourceforge.net/documentation.html.
// Only 16-bit samples are supported.
// 16-bit and 24-bit samples are supported.
// Not all fields in STREAMINFO are supported.
FLAC = 2;
@ -171,8 +174,8 @@ message RecognitionConfig {
// [Optional] The language of the supplied audio as a BCP-47 language tag.
// Example: "en-GB" https://www.rfc-editor.org/rfc/bcp/bcp47.txt
// If omitted, defaults to "en-US". See
// [Language Support](/speech/docs/best-practices#language_support) for
// a list of the currently supported language codes.
// [Language Support](https://cloud.google.com/speech/docs/best-practices#language_support)
// for a list of the currently supported language codes.
string language_code = 3;
// [Optional] Maximum number of recognition hypotheses to be returned.
@ -196,15 +199,19 @@ message RecognitionConfig {
// Provides "hints" to the speech recognizer to favor specific words and phrases
// in the results.
message SpeechContext {
// [Optional] A list of up to 50 phrases of up to 100 characters each to
// provide words and phrases "hints" to the speech recognition so that it is
// more likely to recognize them.
// [Optional] A list of strings containing words and phrases "hints" so that
// the speech recognition is more likely to recognize them. This can be used
// to improve the accuracy for specific words and phrases, for example, if
// specific commands are typically spoken by the user. This can also be used
// to add additional words to the vocabulary of the recognizer. See
// [usage limits](https://cloud.google.com/speech/limits#content).
repeated string phrases = 1;
}
// Contains audio data in the encoding specified in the `RecognitionConfig`.
// Either `content` or `uri` must be supplied. Supplying both or neither
// returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
// returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. See
// [audio limits](https://cloud.google.com/speech/limits#content).
message RecognitionAudio {
oneof audio_source {
// The audio data bytes encoded as specified in
@ -217,14 +224,14 @@ message RecognitionAudio {
// supported, which must be specified in the following format:
// `gs://bucket_name/object_name` (other URI formats return
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
// [Request URIs](/storage/docs/reference-uris).
// [Request URIs](https://cloud.google.com/storage/docs/reference-uris).
string uri = 2;
}
}
// `SyncRecognizeResponse` is the only message returned to the client by
// `SyncRecognize`. It contains the result as zero or more
// sequential `RecognizeResponse` messages.
// `SyncRecognize`. It contains the result as zero or more sequential
// `SpeechRecognitionResult` messages.
message SyncRecognizeResponse {
// [Output-only] Sequential list of transcription results corresponding to
// sequential portions of audio.
@ -232,17 +239,89 @@ message SyncRecognizeResponse {
}
// `AsyncRecognizeResponse` is the only message returned to the client by
// `AsyncRecognize`. It contains the result as zero or more
// sequential `RecognizeResponse` messages.
// `AsyncRecognize`. It contains the result as zero or more sequential
// `SpeechRecognitionResult` messages. It is included in the `result.response`
// field of the `Operation` returned by the `GetOperation` call of the
// `google::longrunning::Operations` service.
message AsyncRecognizeResponse {
// [Output-only] Sequential list of transcription results corresponding to
// sequential portions of audio.
repeated SpeechRecognitionResult results = 2;
}
// `AsyncRecognizeMetadata` describes the progress of a long-running
// `AsyncRecognize` call. It is included in the `metadata` field of the
// `Operation` returned by the `GetOperation` call of the
// `google::longrunning::Operations` service.
message AsyncRecognizeMetadata {
// Approximate percentage of audio processed thus far. Guaranteed to be 100
// when the audio is fully processed and the results are available.
int32 progress_percent = 1;
// Time when the request was received.
google.protobuf.Timestamp start_time = 2;
// Time of the most recent processing update.
google.protobuf.Timestamp last_update_time = 3;
}
// `StreamingRecognizeResponse` is the only message returned to the client by
// `StreamingRecognize`. It contains the result as zero or more
// sequential `RecognizeResponse` messages.
// `StreamingRecognize`. A series of one or more `StreamingRecognizeResponse`
// messages are streamed back to the client.
//
// Here's an example of a series of ten `StreamingRecognizeResponse`s that might
// be returned while processing audio:
//
// 1. endpointer_type: START_OF_SPEECH
//
// 2. results { alternatives { transcript: "tube" } stability: 0.01 }
// result_index: 0
//
// 3. results { alternatives { transcript: "to be a" } stability: 0.01 }
// result_index: 0
//
// 4. results { alternatives { transcript: "to be" } stability: 0.9 }
// results { alternatives { transcript: " or not to be" } stability: 0.01 }
// result_index: 0
//
// 5. results { alternatives { transcript: "to be or not to be"
// confidence: 0.92 }
// alternatives { transcript: "to bee or not to bee" }
// is_final: true }
// result_index: 0
//
// 6. results { alternatives { transcript: " that's" } stability: 0.01 }
// result_index: 1
//
// 7. results { alternatives { transcript: " that is" } stability: 0.9 }
// results { alternatives { transcript: " the question" } stability: 0.01 }
// result_index: 1
//
// 8. endpointer_type: END_OF_SPEECH
//
// 9. results { alternatives { transcript: " that is the question"
// confidence: 0.98 }
// alternatives { transcript: " that was the question" }
// is_final: true }
// result_index: 1
//
// 10. endpointer_type: END_OF_AUDIO
//
// Notes:
//
// - Only two of the above responses #5 and #9 contain final results, they are
// indicated by `is_final: true`. Concatenating these together generates the
// full transcript: "to be or not to be that is the question".
//
// - The others contain interim `results`. #4 and #7 contain two interim
// `results`, the first portion has a high stability and is less likely to
// change, the second portion has a low stability and is very likely to
// change. A UI designer might choose to show only high stability `results`.
//
// - The `result_index` indicates the portion of audio that has had final
// results returned, and is no longer being processed. For example, the
// `results` in #6 and later correspond to the portion of audio after
// "to be or not to be".
message StreamingRecognizeResponse {
// Indicates the type of endpointer event.
enum EndpointerType {
@ -276,7 +355,7 @@ message StreamingRecognizeResponse {
repeated StreamingRecognitionResult results = 2;
// [Output-only] Indicates the lowest index in the `results` array that has
// changed. The repeated `SpeechRecognitionResult` results overwrite past
// changed. The repeated `StreamingRecognitionResult` results overwrite past
// results at this index and higher.
int32 result_index = 3;
@ -284,16 +363,16 @@ message StreamingRecognizeResponse {
EndpointerType endpointer_type = 4;
}
// A speech recognition result corresponding to a portion of the audio that is
// currently being processed.
// A streaming speech recognition result corresponding to a portion of the audio
// that is currently being processed.
message StreamingRecognitionResult {
// [Output-only] May contain one or more recognition hypotheses (up to the
// maximum specified in `max_alternatives`).
repeated SpeechRecognitionAlternative alternatives = 1;
// [Output-only] If `false`, this `SpeechRecognitionResult` represents an
// [Output-only] If `false`, this `StreamingRecognitionResult` represents an
// interim result that may change. If `true`, this is the final time the
// speech service will return this particular `SpeechRecognitionResult`,
// speech service will return this particular `StreamingRecognitionResult`,
// the recognizer will not return any further hypotheses for this portion of
// the transcript and corresponding audio.
bool is_final = 2;

Write Preview
Loading…
Cancel
Save