speech/snippets/multichannel.go (42 lines of code) (raw):
// Copyright 2019 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// https://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
// Package snippets contains speech examples.
package snippets
import (
speech "cloud.google.com/go/speech/apiv1"
"cloud.google.com/go/speech/apiv1/speechpb"
"context"
"fmt"
"io"
"os"
)
// [START speech_transcribe_multichannel_beta]
// transcribeMultichannel generates a transcript from a multichannel speech file and tags the speech from each channel.
func transcribeMultichannel(w io.Writer) error {
ctx := context.Background()
client, err := speech.NewClient(ctx)
if err != nil {
return fmt.Errorf("NewClient: %w", err)
}
defer client.Close()
data, err := os.ReadFile("../testdata/commercial_stereo.wav")
if err != nil {
return fmt.Errorf("ReadFile: %w", err)
}
resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
Config: &speechpb.RecognitionConfig{
Encoding: speechpb.RecognitionConfig_LINEAR16,
SampleRateHertz: 44100,
LanguageCode: "en-US",
AudioChannelCount: 2,
EnableSeparateRecognitionPerChannel: true,
},
Audio: &speechpb.RecognitionAudio{
AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
},
})
if err != nil {
return fmt.Errorf("Recognize: %w", err)
}
// Print the results.
for _, result := range resp.Results {
for _, alt := range result.Alternatives {
fmt.Fprintf(w, "Channel %v: %v\n", result.ChannelTag, alt.Transcript)
}
}
return nil
}
// [END speech_transcribe_multichannel_beta]