Skip to content

Commit

Permalink
docs: Add documentation for latest models to RecognitionConfig
Browse files Browse the repository at this point in the history 
PiperOrigin-RevId: 446200223
  • Loading branch information
Google APIs authored and Copybara-Service committed May 3, 2022
1 parent 27ee094 commit 4f586ea
Show file tree
Hide file tree
Showing 2 changed files with 84 additions and 50 deletions.
66 changes: 42 additions & 24 deletions google/cloud/speech/v1/cloud_speech.proto
View file
Expand Up @@ -36,7 +36,8 @@ option objc_class_prefix = "GCS";
// Service that implements Google Cloud Speech API.
service Speech {
option (google.api.default_host) = "speech.googleapis.com";
option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform";
option (google.api.oauth_scopes) =
"https://www.googleapis.com/auth/cloud-platform";

// Performs synchronous speech recognition: receive results after all audio
// has been sent and processed.
Expand All @@ -54,7 +55,8 @@ service Speech {
// a `LongRunningRecognizeResponse` message.
// For more information on asynchronous speech recognition, see the
// [how-to](https://cloud.google.com/speech-to-text/docs/async-recognize).
rpc LongRunningRecognize(LongRunningRecognizeRequest) returns (google.longrunning.Operation) {
rpc LongRunningRecognize(LongRunningRecognizeRequest)
returns (google.longrunning.Operation) {
option (google.api.http) = {
post: "/v1/speech:longrunningrecognize"
body: "*"
Expand All @@ -68,8 +70,8 @@ service Speech {

// Performs bidirectional streaming speech recognition: receive results while
// sending audio. This method is only available via the gRPC API (not REST).
rpc StreamingRecognize(stream StreamingRecognizeRequest) returns (stream StreamingRecognizeResponse) {
}
rpc StreamingRecognize(stream StreamingRecognizeRequest)
returns (stream StreamingRecognizeResponse) {}
}

// The top-level message sent by the client for the `Recognize` method.
Expand All @@ -93,7 +95,8 @@ message LongRunningRecognizeRequest {
RecognitionAudio audio = 2 [(google.api.field_behavior) = REQUIRED];

// Optional. Specifies an optional destination for the recognition results.
TranscriptOutputConfig output_config = 4 [(google.api.field_behavior) = OPTIONAL];
TranscriptOutputConfig output_config = 4
[(google.api.field_behavior) = OPTIONAL];
}

// Specifies an optional destination for the recognition results.
Expand Down Expand Up @@ -193,7 +196,8 @@ message RecognitionConfig {
// an `AudioEncoding` when you send send `FLAC` or `WAV` audio, the
// encoding configuration must match the encoding described in the audio
// header; otherwise the request returns an
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error code.
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
// code.
enum AudioEncoding {
// Not specified.
ENCODING_UNSPECIFIED = 0;
Expand Down Expand Up @@ -246,7 +250,8 @@ message RecognitionConfig {

// Encoding of audio data sent in all `RecognitionAudio` messages.
// This field is optional for `FLAC` and `WAV` audio files and required
// for all other audio formats. For details, see [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding].
// for all other audio formats. For details, see
// [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding].
AudioEncoding encoding = 1;

// Sample rate in Hertz of the audio data sent in all
Expand All @@ -255,7 +260,8 @@ message RecognitionConfig {
// source to 16000 Hz. If that's not possible, use the native sample rate of
// the audio source (instead of re-sampling).
// This field is optional for FLAC and WAV audio files, but is
// required for all other audio formats. For details, see [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding].
// required for all other audio formats. For details, see
// [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding].
int32 sample_rate_hertz = 2;

// The number of channels in the input audio data.
Expand Down Expand Up @@ -383,6 +389,19 @@ message RecognitionConfig {
// <td><b>Description</b></td>
// </tr>
// <tr>
// <td><code>latest_long</code></td>
// <td>Best for long form content like media or conversation.</td>
// </tr>
// <tr>
// <td><code>latest_short</code></td>
// <td>Best for short form content like commands or single shot directed
// speech.</td>
// </tr>
// <tr>
// <td><code>command_and_search</code></td>
// <td>Best for short queries such as voice commands or voice search.</td>
// </tr>
// <tr>
// <td><code>command_and_search</code></td>
// <td>Best for short queries such as voice commands or voice search.</td>
// </tr>
Expand Down Expand Up @@ -436,10 +455,8 @@ message SpeakerDiarizationConfig {
int32 max_speaker_count = 3;

// Output only. Unused.
int32 speaker_tag = 5 [
deprecated = true,
(google.api.field_behavior) = OUTPUT_ONLY
];
int32 speaker_tag = 5
[deprecated = true, (google.api.field_behavior) = OUTPUT_ONLY];
}

// Description of audio data to be recognized.
Expand Down Expand Up @@ -599,8 +616,8 @@ message SpeechContext {

// 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]. See
// [content limits](https://cloud.google.com/speech-to-text/quotas#content).
// returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
// See [content limits](https://cloud.google.com/speech-to-text/quotas#content).
message RecognitionAudio {
// The audio source, which is either inline content or a Google Cloud
// Storage uri.
Expand All @@ -615,8 +632,9 @@ message RecognitionAudio {
// Currently, only Google Cloud Storage URIs are
// 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](https://cloud.google.com/storage/docs/reference-uris).
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
// For more information, see [Request
// URIs](https://cloud.google.com/storage/docs/reference-uris).
string uri = 2;
}
}
Expand Down Expand Up @@ -667,8 +685,8 @@ message LongRunningRecognizeMetadata {
// Time of the most recent processing update.
google.protobuf.Timestamp last_update_time = 3;

// Output only. The URI of the audio file being transcribed. Empty if the audio was sent
// as byte content.
// Output only. The URI of the audio file being transcribed. Empty if the
// audio was sent as byte content.
string uri = 4 [(google.api.field_behavior) = OUTPUT_ONLY];
}

Expand Down Expand Up @@ -787,9 +805,9 @@ message StreamingRecognitionResult {
// For audio_channel_count = N, its output values can range from '1' to 'N'.
int32 channel_tag = 5;

// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag
// of the language in this result. This language code was detected to have
// the most likelihood of being spoken in the audio.
// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
// language tag of the language in this result. This language code was
// detected to have the most likelihood of being spoken in the audio.
string language_code = 6 [(google.api.field_behavior) = OUTPUT_ONLY];
}

Expand All @@ -810,9 +828,9 @@ message SpeechRecognitionResult {
// beginning of the audio.
google.protobuf.Duration result_end_time = 4;

// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag
// of the language in this result. This language code was detected to have
// the most likelihood of being spoken in the audio.
// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
// language tag of the language in this result. This language code was
// detected to have the most likelihood of being spoken in the audio.
string language_code = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
}

Expand Down
68 changes: 42 additions & 26 deletions google/cloud/speech/v1p1beta1/cloud_speech.proto
View file
Expand Up @@ -37,7 +37,8 @@ option objc_class_prefix = "GCS";
// Service that implements Google Cloud Speech API.
service Speech {
option (google.api.default_host) = "speech.googleapis.com";
option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform";
option (google.api.oauth_scopes) =
"https://www.googleapis.com/auth/cloud-platform";

// Performs synchronous speech recognition: receive results after all audio
// has been sent and processed.
Expand All @@ -55,7 +56,8 @@ service Speech {
// a `LongRunningRecognizeResponse` message.
// For more information on asynchronous speech recognition, see the
// [how-to](https://cloud.google.com/speech-to-text/docs/async-recognize).
rpc LongRunningRecognize(LongRunningRecognizeRequest) returns (google.longrunning.Operation) {
rpc LongRunningRecognize(LongRunningRecognizeRequest)
returns (google.longrunning.Operation) {
option (google.api.http) = {
post: "/v1p1beta1/speech:longrunningrecognize"
body: "*"
Expand All @@ -69,8 +71,8 @@ service Speech {

// Performs bidirectional streaming speech recognition: receive results while
// sending audio. This method is only available via the gRPC API (not REST).
rpc StreamingRecognize(stream StreamingRecognizeRequest) returns (stream StreamingRecognizeResponse) {
}
rpc StreamingRecognize(stream StreamingRecognizeRequest)
returns (stream StreamingRecognizeResponse) {}
}

// The top-level message sent by the client for the `Recognize` method.
Expand All @@ -94,7 +96,8 @@ message LongRunningRecognizeRequest {
RecognitionAudio audio = 2 [(google.api.field_behavior) = REQUIRED];

// Optional. Specifies an optional destination for the recognition results.
TranscriptOutputConfig output_config = 4 [(google.api.field_behavior) = OPTIONAL];
TranscriptOutputConfig output_config = 4
[(google.api.field_behavior) = OPTIONAL];
}

// Specifies an optional destination for the recognition results.
Expand Down Expand Up @@ -194,7 +197,8 @@ message RecognitionConfig {
// an `AudioEncoding` when you send send `FLAC` or `WAV` audio, the
// encoding configuration must match the encoding described in the audio
// header; otherwise the request returns an
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error code.
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
// code.
enum AudioEncoding {
// Not specified.
ENCODING_UNSPECIFIED = 0;
Expand Down Expand Up @@ -253,7 +257,8 @@ message RecognitionConfig {

// Encoding of audio data sent in all `RecognitionAudio` messages.
// This field is optional for `FLAC` and `WAV` audio files and required
// for all other audio formats. For details, see [AudioEncoding][google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding].
// for all other audio formats. For details, see
// [AudioEncoding][google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding].
AudioEncoding encoding = 1;

// Sample rate in Hertz of the audio data sent in all
Expand All @@ -262,7 +267,8 @@ message RecognitionConfig {
// source to 16000 Hz. If that's not possible, use the native sample rate of
// the audio source (instead of re-sampling).
// This field is optional for FLAC and WAV audio files, but is
// required for all other audio formats. For details, see [AudioEncoding][google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding].
// required for all other audio formats. For details, see
// [AudioEncoding][google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding].
int32 sample_rate_hertz = 2;

// The number of channels in the input audio data.
Expand Down Expand Up @@ -407,6 +413,15 @@ message RecognitionConfig {
// <td><b>Description</b></td>
// </tr>
// <tr>
// <td><code>latest_long</code></td>
// <td>Best for long form content like media or conversation.</td>
// </tr>
// <tr>
// <td><code>latest_short</code></td>
// <td>Best for short form content like commands or single shot directed
// speech.</td>
// </tr>
// <tr>
// <td><code>command_and_search</code></td>
// <td>Best for short queries such as voice commands or voice search.</td>
// </tr>
Expand Down Expand Up @@ -460,10 +475,8 @@ message SpeakerDiarizationConfig {
int32 max_speaker_count = 3;

// Output only. Unused.
int32 speaker_tag = 5 [
deprecated = true,
(google.api.field_behavior) = OUTPUT_ONLY
];
int32 speaker_tag = 5
[deprecated = true, (google.api.field_behavior) = OUTPUT_ONLY];
}

// Description of audio data to be recognized.
Expand Down Expand Up @@ -627,8 +640,8 @@ message SpeechContext {

// 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]. See
// [content limits](https://cloud.google.com/speech-to-text/quotas#content).
// returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
// See [content limits](https://cloud.google.com/speech-to-text/quotas#content).
message RecognitionAudio {
// The audio source, which is either inline content or a Google Cloud
// Storage uri.
Expand All @@ -643,8 +656,9 @@ message RecognitionAudio {
// Currently, only Google Cloud Storage URIs are
// 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](https://cloud.google.com/storage/docs/reference-uris).
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
// For more information, see [Request
// URIs](https://cloud.google.com/storage/docs/reference-uris).
string uri = 2;
}
}
Expand Down Expand Up @@ -695,12 +709,14 @@ message LongRunningRecognizeMetadata {
// Time of the most recent processing update.
google.protobuf.Timestamp last_update_time = 3;

// Output only. The URI of the audio file being transcribed. Empty if the audio was sent
// as byte content.
// Output only. The URI of the audio file being transcribed. Empty if the
// audio was sent as byte content.
string uri = 4 [(google.api.field_behavior) = OUTPUT_ONLY];

// Output only. A copy of the TranscriptOutputConfig if it was set in the request.
TranscriptOutputConfig output_config = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. A copy of the TranscriptOutputConfig if it was set in the
// request.
TranscriptOutputConfig output_config = 5
[(google.api.field_behavior) = OUTPUT_ONLY];
}

// `StreamingRecognizeResponse` is the only message returned to the client by
Expand Down Expand Up @@ -818,9 +834,9 @@ message StreamingRecognitionResult {
// For audio_channel_count = N, its output values can range from '1' to 'N'.
int32 channel_tag = 5;

// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag
// of the language in this result. This language code was detected to have
// the most likelihood of being spoken in the audio.
// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
// language tag of the language in this result. This language code was
// detected to have the most likelihood of being spoken in the audio.
string language_code = 6 [(google.api.field_behavior) = OUTPUT_ONLY];
}

Expand All @@ -841,9 +857,9 @@ message SpeechRecognitionResult {
// beginning of the audio.
google.protobuf.Duration result_end_time = 4;

// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag
// of the language in this result. This language code was detected to have
// the most likelihood of being spoken in the audio.
// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
// language tag of the language in this result. This language code was
// detected to have the most likelihood of being spoken in the audio.
string language_code = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
}

Expand Down

0 comments on commit 4f586ea

Please sign in to comment.