This repository has been archived by the owner on Feb 18, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 291
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add streaming microphone sample for Speech (#87)
Add streaming microphone sample for Speech
- Loading branch information
1 parent
f2c42b5
commit 5760658
Showing
3 changed files
with
258 additions
and
108 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,129 @@ | ||
| /** | ||
| * Copyright 2017, Google, Inc. | ||
| * 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 | ||
| * | ||
| * http://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. | ||
| */ | ||
|
|
||
| /** | ||
| * This application demonstrates how to perform basic recognize operations with | ||
| * with the Google Cloud Speech API. | ||
| * | ||
| * For more information, see the README.md under /speech and the documentation | ||
| * at https://cloud.google.com/speech/docs. | ||
| */ | ||
|
|
||
| 'use strict'; | ||
|
|
||
| /** | ||
| * Note: Correct microphone settings is required: check enclosed link, and make | ||
| * sure the following conditions are met: | ||
| * 1. SoX must be installed and available in your $PATH- it can be found here: | ||
| * http://sox.sourceforge.net/ | ||
| * 2. Microphone must be working | ||
| * 3. Encoding, sampleRateHertz, and # of channels must match header of audio file you're | ||
| * recording to. | ||
| * 4. Get Node-Record-lpcm16 https://www.npmjs.com/package/node-record-lpcm16 | ||
| * More Info: https://cloud.google.com/speech-to-text/docs/streaming-recognize | ||
| */ | ||
|
|
||
| // const encoding = 'LINEAR16'; | ||
| // const sampleRateHertz = 16000; | ||
| // const languageCode = 'en-US'; | ||
|
|
||
| function microphoneStream(encoding, sampleRateHertz, languageCode) { | ||
| // [START micStreamRecognize] | ||
|
|
||
| // Node-Record-lpcm16 | ||
| const record = require('node-record-lpcm16'); | ||
|
|
||
| // Imports the Google Cloud client library | ||
| const speech = require('@google-cloud/speech'); | ||
|
|
||
| const config = { | ||
| encoding: encoding, | ||
| sampleRateHertz: sampleRateHertz, | ||
| languageCode: languageCode, | ||
| }; | ||
|
|
||
| const request = { | ||
| config, | ||
| interimResults: false, //Get interim results from stream | ||
| }; | ||
|
|
||
| // Creates a client | ||
| const client = new speech.SpeechClient(); | ||
|
|
||
| // Create a recognize stream | ||
| const recognizeStream = client | ||
| .streamingRecognize(request) | ||
| .on('error', console.error) | ||
| .on('data', data => | ||
| process.stdout.write( | ||
| data.results[0] && data.results[0].alternatives[0] | ||
| ? `Transcription: ${data.results[0].alternatives[0].transcript}\n` | ||
| : `\n\nReached transcription time limit, press Ctrl+C\n` | ||
| ) | ||
| ); | ||
|
|
||
| // Start recording and send the microphone input to the Speech API | ||
| record | ||
| .start({ | ||
| sampleRateHertz: sampleRateHertz, | ||
| threshold: 0, //silence threshold | ||
| recordProgram: 'rec', // Try also "arecord" or "sox" | ||
| silence: '5.0', //seconds of silence before ending | ||
| }) | ||
| .on('error', console.error) | ||
| .pipe(recognizeStream); | ||
|
|
||
| console.log('Listening, press Ctrl+C to stop.'); | ||
| // [END micStreamRecognize] | ||
| } | ||
|
|
||
| require(`yargs`) | ||
| .demand(1) | ||
| .command( | ||
| `micStreamRecognize`, | ||
| `Streams audio input from microphone, translates to text`, | ||
| {}, | ||
| opts => | ||
| microphoneStream(opts.encoding, opts.sampleRateHertz, opts.languageCode) | ||
| ) | ||
| .options({ | ||
| encoding: { | ||
| alias: 'e', | ||
| default: 'LINEAR16', | ||
| global: true, | ||
| requiresArg: true, | ||
| type: 'string', | ||
| }, | ||
| sampleRateHertz: { | ||
| alias: 'r', | ||
| default: 16000, | ||
| global: true, | ||
| requiresArg: true, | ||
| type: 'number', | ||
| }, | ||
| languageCode: { | ||
| alias: 'l', | ||
| default: 'en-US', | ||
| global: true, | ||
| requiresArg: true, | ||
| type: 'string', | ||
| }, | ||
| }) | ||
| .example(`node $0 micStreamRecognize`) | ||
| .wrap(120) | ||
| .recommendCommands() | ||
| .epilogue(`For more information, see https://cloud.google.com/speech/docs`) | ||
| .help() | ||
| .strict().argv; |
Oops, something went wrong.