docs: updated description of sample_rate_hertz

Google APIs · copybara-github · commit b38aab7e8498 · 2025-06-10T05:31:03.000-07:00
feat: add denoiser related configuration

PiperOrigin-RevId: 769585786
diff --git a/google/cloud/speech/v1/BUILD.bazel b/google/cloud/speech/v1/BUILD.bazel
@@ -348,7 +348,6 @@ load(
 
 csharp_proto_library(
     name = "speech_csharp_proto",
-    extra_opts = [],
     deps = [":speech_proto"],
 )
 
diff --git a/google/cloud/speech/v1p1beta1/BUILD.bazel b/google/cloud/speech/v1p1beta1/BUILD.bazel
@@ -348,7 +348,6 @@ load(
 
 csharp_proto_library(
     name = "speech_csharp_proto",
-    extra_opts = [],
     deps = [":speech_proto"],
 )
 
diff --git a/google/cloud/speech/v2/BUILD.bazel b/google/cloud/speech/v2/BUILD.bazel
@@ -348,6 +348,7 @@ load(
 
 csharp_proto_library(
     name = "speech_csharp_proto",
+    extra_opts = [],
     deps = [":speech_proto"],
 )
 
diff --git a/google/cloud/speech/v2/cloud_speech.proto b/google/cloud/speech/v2/cloud_speech.proto
@@ -762,9 +762,9 @@ message ExplicitDecodingConfig {
   AudioEncoding encoding = 1 [(google.api.field_behavior) = REQUIRED];
 
   // Optional. Sample rate in Hertz of the audio data sent for recognition.
-  // 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).
+  // Valid values are: 8000-48000, and 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 resampling).
   // Note that this field is marked as OPTIONAL for backward compatibility
   // reasons. It is (and has always been) effectively REQUIRED.
   int32 sample_rate_hertz = 2 [(google.api.field_behavior) = OPTIONAL];
@@ -921,6 +921,21 @@ message SpeechAdaptation {
   repeated CustomClass custom_classes = 2;
 }
 
+// Denoiser config. May not be supported for all models and may
+// have no effect.
+message DenoiserConfig {
+  // Denoise audio before sending to the transcription model.
+  bool denoise_audio = 1;
+
+  // Signal-to-Noise Ratio (SNR) threshold for the denoiser. Here SNR means the
+  // loudness of the speech signal. Audio with an SNR below this threshold,
+  // meaning the speech is too quiet, will be prevented from being sent to the
+  // transcription model.
+  //
+  // If snr_threshold=0, no filtering will be applied.
+  float snr_threshold = 2;
+}
+
 // Provides information to the Recognizer that specifies how to process the
 // recognition request.
 message RecognitionConfig {
@@ -977,6 +992,10 @@ message RecognitionConfig {
   // the given audio to the desired language for supported models.
   TranslationConfig translation_config = 15
       [(google.api.field_behavior) = OPTIONAL];
+
+  // Optional. Optional denoiser config. May not be supported for all models
+  // and may have no effect.
+  DenoiserConfig denoiser_config = 16 [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Request message for the
diff --git a/google/cloud/speech/v2/locations_metadata.proto b/google/cloud/speech/v2/locations_metadata.proto
@@ -21,7 +21,7 @@ option java_multiple_files = true;
 option java_outer_classname = "LocationsMetadataProto";
 option java_package = "com.google.cloud.speech.v2";
 
-// Representes a singular feature of a model. If the feature is `recognizer`,
+// Represents a singular feature of a model. If the feature is `recognizer`,
 // the release_state of the feature represents the release_state of the model
 message ModelFeature {
   // The name of the feature (Note: the feature can be `recognizer`)

Original file line number	Diff line number	Diff line change
`@@ -348,7 +348,6 @@ load(`
`348`	`348`
`349`	`349`	`csharp_proto_library(`
`350`	`350`	`name = "speech_csharp_proto",`
`351`		`- extra_opts = [],`
`352`	`351`	`deps = [":speech_proto"],`
`353`	`352`	`)`
`354`	`353`
Original file line number	Diff line number	Diff line change
`@@ -348,6 +348,7 @@ load(`
`348`	`348`
`349`	`349`	`csharp_proto_library(`
`350`	`350`	`name = "speech_csharp_proto",`
	`351`	`+ extra_opts = [],`
`351`	`352`	`deps = [":speech_proto"],`
`352`	`353`	`)`
`353`	`354`