speech/captionasync/captionasync.go (95 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.
// Command captionasync sends audio data to the Google Speech API
// and prints its transcript.
package main
import (
"context"
"fmt"
"io"
"log"
"os"
"strings"
speech "cloud.google.com/go/speech/apiv1"
"cloud.google.com/go/speech/apiv1/speechpb"
)
const usage = `Usage: captionasync <audiofile>
Audio file must be a 16-bit signed little-endian encoded
with a sample rate of 16000.
The path to the audio file may be a GCS URI (gs://...).`
func main() {
if len(os.Args) < 2 {
fmt.Fprintln(os.Stderr, usage)
os.Exit(2)
}
var sendFunc func(io.Writer, *speech.Client, string) error
path := os.Args[1]
if strings.Contains(path, "://") {
sendFunc = sendGCS
} else {
sendFunc = send
}
ctx := context.Background()
client, err := speech.NewClient(ctx)
if err != nil {
log.Fatal(err)
}
defer client.Close()
if err := sendFunc(os.Stdout, client, os.Args[1]); err != nil {
log.Fatal(err)
}
}
// [START speech_transcribe_async]
func send(w io.Writer, client *speech.Client, filename string) error {
ctx := context.Background()
data, err := os.ReadFile(filename)
if err != nil {
return err
}
// Send the contents of the audio file with the encoding and
// and sample rate information to be transcripted.
req := &speechpb.LongRunningRecognizeRequest{
Config: &speechpb.RecognitionConfig{
Encoding: speechpb.RecognitionConfig_LINEAR16,
SampleRateHertz: 16000,
LanguageCode: "en-US",
},
Audio: &speechpb.RecognitionAudio{
AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
},
}
op, err := client.LongRunningRecognize(ctx, req)
if err != nil {
return err
}
resp, err := op.Wait(ctx)
if err != nil {
return err
}
// Print the results.
for _, result := range resp.Results {
for _, alt := range result.Alternatives {
fmt.Fprintf(w, "\"%v\" (confidence=%3f)\n", alt.Transcript, alt.Confidence)
}
}
return nil
}
// [END speech_transcribe_async]
// [START speech_transcribe_async_gcs]
func sendGCS(w io.Writer, client *speech.Client, gcsURI string) error {
ctx := context.Background()
// Send the contents of the audio file with the encoding and
// and sample rate information to be transcripted.
req := &speechpb.LongRunningRecognizeRequest{
Config: &speechpb.RecognitionConfig{
Encoding: speechpb.RecognitionConfig_LINEAR16,
SampleRateHertz: 16000,
LanguageCode: "en-US",
},
Audio: &speechpb.RecognitionAudio{
AudioSource: &speechpb.RecognitionAudio_Uri{Uri: gcsURI},
},
}
op, err := client.LongRunningRecognize(ctx, req)
if err != nil {
return err
}
resp, err := op.Wait(ctx)
if err != nil {
return err
}
// Print the results.
for _, result := range resp.Results {
for _, alt := range result.Alternatives {
fmt.Fprintf(w, "\"%v\" (confidence=%3f)\n", alt.Transcript, alt.Confidence)
}
}
return nil
}
// [END speech_transcribe_async_gcs]