From 48380c60c3398a8d64fb3b727f656086482b3905 Mon Sep 17 00:00:00 2001
From: Brad Miro <bmiro@google.com>
Date: Mon, 11 Nov 2019 18:53:50 -0500
Subject: [PATCH] feat(samples): bump auto-punctuation sample to v1 and move
 diarization to v1 (#463)

* bumped diarization and autocapitalization samples to v1

* Remove extra commited file

* fixed linting error
---
 speech/recognize.js                  | 72 +++++++++++++++++++++++++++-
 speech/system-test/recognize.test.js |  5 ++
 2 files changed, 75 insertions(+), 2 deletions(-)

diff --git a/speech/recognize.js b/speech/recognize.js
index ac3cfa5b6c4..d0274ad5001 100644
--- a/speech/recognize.js
+++ b/speech/recognize.js
@@ -544,12 +544,12 @@ async function syncRecognizeWithAutoPunctuation(
   languageCode
 ) {
   // [START speech_transcribe_auto_punctuation]
-  // Imports the Google Cloud client library for Beta API
+  // Imports the Google Cloud client library for API
   /**
    * TODO(developer): Update client library import to use new
    * version of API when desired features become available
    */
-  const speech = require('@google-cloud/speech').v1p1beta1;
+  const speech = require('@google-cloud/speech');
   const fs = require('fs');
 
   // Creates a client
@@ -712,6 +712,62 @@ async function syncRecognizeWithMultiChannelGCS(gcsUri) {
   // [END speech_transcribe_multichannel_gcs]
 }
 
+async function speechTranscribeDiarization(fileName) {
+  // [START speech_transcribe_diarization]
+  const fs = require('fs');
+
+  // Imports the Google Cloud client library
+  const speech = require('@google-cloud/speech');
+
+  // Creates a client
+  const client = new speech.SpeechClient();
+
+  // Set config for Diarization
+  const diarizationConfig = {
+    enableSpeakerDiarization: true,
+    maxSpeakerCount: 2,
+  };
+
+  const config = {
+    encoding: `LINEAR16`,
+    sampleRateHertz: 8000,
+    languageCode: `en-US`,
+    diarizationConfig: diarizationConfig,
+    model: `phone_call`,
+  };
+
+  /**
+   * TODO(developer): Uncomment the following lines before running the sample.
+   */
+  // const fileName = 'Local path to audio file, e.g. /path/to/audio.raw';
+
+  const audio = {
+    content: fs.readFileSync(fileName).toString('base64'),
+  };
+
+  const request = {
+    config: config,
+    audio: audio,
+  };
+
+  const [response] = await client.recognize(request);
+  const transcription = response.results
+    .map(result => result.alternatives[0].transcript)
+    .join('\n');
+  console.log(`Transcription: ${transcription}`);
+  console.log(`Speaker Diarization:`);
+  const result = response.results[response.results.length - 1];
+  const wordsInfo = result.alternatives[0].words;
+  // Note: The transcript within each result is separate and sequential per result.
+  // However, the words list within an alternative includes all the words
+  // from all the results thus far. Thus, to get all the words with speaker
+  // tags, you only have to take the words list from the last result:
+  wordsInfo.forEach(a =>
+    console.log(` word: ${a.word}, speakerTag: ${a.speakerTag}`)
+  );
+  // [END speech_transcribe_diarization]
+}
+
 require(`yargs`) // eslint-disable-line
   .demand(1)
   .command(
@@ -883,6 +939,12 @@ require(`yargs`) // eslint-disable-line
         opts.languageCode
       )
   )
+  .command(
+    `Diarization`,
+    `Isolate distinct speakers in an audio file`,
+    {},
+    opts => speechTranscribeDiarization(opts.speechFile)
+  )
   .options({
     encoding: {
       alias: 'e',
@@ -905,6 +967,12 @@ require(`yargs`) // eslint-disable-line
       requiresArg: true,
       type: 'string',
     },
+    speechFile: {
+      alias: 'f',
+      global: true,
+      requiresArg: false,
+      type: 'string',
+    },
   })
   .example(`node $0 sync ./resources/audio.raw -e LINEAR16 -r 16000`)
   .example(`node $0 async-gcs gs://gcs-test-data/vr.flac -e FLAC -r 16000`)
diff --git a/speech/system-test/recognize.test.js b/speech/system-test/recognize.test.js
index 59a696ce350..3a96c344db3 100644
--- a/speech/system-test/recognize.test.js
+++ b/speech/system-test/recognize.test.js
@@ -132,4 +132,9 @@ describe('Recognize', () => {
     );
     assert.match(output, /Channel Tag: 2/);
   });
+
+  it('should run speech diarization on a local file', async () => {
+    const output = execSync(`${cmd} Diarization -f ${filepath2}`);
+    assert.match(output, /speakerTag:/);
+  });
 });