Skip to content

Commit 7cb813c

Browse files
beccasaurusAce Nassri
beccasaurus
authored and
Ace Nassri
committed
Add Speech Recognition v1p1beta1 samples (#33)
* Add Speech Recognition v1p1beta1 samples * Upgrade eslint-plugin-prettier to ^2.6.0
1 parent 91bb10a commit 7cb813c

3 files changed

Lines changed: 255 additions & 0 deletions

File tree

‎speech/recognize.v1p1beta1.js‎

Lines changed: 196 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,196 @@
1+
/**
2+
* Copyright 2017, Google, Inc.
3+
* Licensed under the Apache License, Version 2.0 (the "License");
4+
* you may not use this file except in compliance with the License.
5+
* You may obtain a copy of the License at
6+
*
7+
* http://www.apache.org/licenses/LICENSE-2.0
8+
*
9+
* Unless required by applicable law or agreed to in writing, software
10+
* distributed under the License is distributed on an "AS IS" BASIS,
11+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
* See the License for the specific language governing permissions and
13+
* limitations under the License.
14+
*/
15+
16+
/**
17+
* This application demonstrates how to perform basic recognize operations with
18+
* with the Google Cloud Speech API.
19+
*
20+
* For more information, see the README.md under /speech and the documentation
21+
* at https://cloud.google.com/speech/docs.
22+
*/
23+
24+
'use strict';
25+
26+
function syncRecognizeModelSelection(
27+
filename,
28+
model,
29+
encoding,
30+
sampleRateHertz,
31+
languageCode
32+
) {
33+
// [START speech_transcribe_model_selection]
34+
// Imports the Google Cloud client library
35+
const fs = require('fs');
36+
const speech = require('@google-cloud/speech').v1p1beta1;
37+
38+
// Creates a client
39+
const client = new speech.SpeechClient();
40+
41+
/**
42+
* TODO(developer): Uncomment the following lines before running the sample.
43+
*/
44+
// const filename = 'Local path to audio file, e.g. /path/to/audio.raw';
45+
// const model = 'Model to use, e.g. phone_call, video, default';
46+
// const encoding = 'Encoding of the audio file, e.g. LINEAR16';
47+
// const sampleRateHertz = 16000;
48+
// const languageCode = 'BCP-47 language code, e.g. en-US';
49+
50+
const config = {
51+
encoding: encoding,
52+
sampleRateHertz: sampleRateHertz,
53+
languageCode: languageCode,
54+
model: model,
55+
};
56+
const audio = {
57+
content: fs.readFileSync(filename).toString('base64'),
58+
};
59+
60+
const request = {
61+
config: config,
62+
audio: audio,
63+
};
64+
65+
// Detects speech in the audio file
66+
client
67+
.recognize(request)
68+
.then(data => {
69+
const response = data[0];
70+
const transcription = response.results
71+
.map(result => result.alternatives[0].transcript)
72+
.join('\n');
73+
console.log(`Transcription: `, transcription);
74+
})
75+
.catch(err => {
76+
console.error('ERROR:', err);
77+
});
78+
// [END speech_transcribe_model_selection]
79+
}
80+
81+
function syncRecognizeModelSelectionGCS(
82+
gcsUri,
83+
model,
84+
encoding,
85+
sampleRateHertz,
86+
languageCode
87+
) {
88+
// [START speech_transcribe_model_selection_gcs]
89+
// Imports the Google Cloud client library
90+
const speech = require('@google-cloud/speech').v1p1beta1;
91+
92+
// Creates a client
93+
const client = new speech.SpeechClient();
94+
95+
/**
96+
* TODO(developer): Uncomment the following lines before running the sample.
97+
*/
98+
// const gcsUri = 'gs://my-bucket/audio.raw';
99+
// const model = 'Model to use, e.g. phone_call, video, default';
100+
// const encoding = 'Encoding of the audio file, e.g. LINEAR16';
101+
// const sampleRateHertz = 16000;
102+
// const languageCode = 'BCP-47 language code, e.g. en-US';
103+
104+
const config = {
105+
encoding: encoding,
106+
sampleRateHertz: sampleRateHertz,
107+
languageCode: languageCode,
108+
model: model,
109+
};
110+
const audio = {
111+
uri: gcsUri,
112+
};
113+
114+
const request = {
115+
config: config,
116+
audio: audio,
117+
};
118+
119+
// Detects speech in the audio file
120+
client
121+
.recognize(request)
122+
.then(data => {
123+
const response = data[0];
124+
const transcription = response.results
125+
.map(result => result.alternatives[0].transcript)
126+
.join('\n');
127+
console.log(`Transcription: `, transcription);
128+
})
129+
.catch(err => {
130+
console.error('ERROR:', err);
131+
});
132+
// [END speech_transcribe_model_selection_gcs]
133+
}
134+
135+
require(`yargs`)
136+
.demand(1)
137+
.command(
138+
`sync-model <filename> <model>`,
139+
`Detects speech in a local audio file using provided model.`,
140+
{},
141+
opts =>
142+
syncRecognizeModelSelection(
143+
opts.filename,
144+
opts.model,
145+
opts.encoding,
146+
opts.sampleRateHertz,
147+
opts.languageCode
148+
)
149+
)
150+
.command(
151+
`sync-model-gcs <gcsUri> <model>`,
152+
`Detects speech in an audio file located in a Google Cloud Storage bucket using provided model.`,
153+
{},
154+
opts =>
155+
syncRecognizeModelSelectionGCS(
156+
opts.gcsUri,
157+
opts.model,
158+
opts.encoding,
159+
opts.sampleRateHertz,
160+
opts.languageCode
161+
)
162+
)
163+
.options({
164+
encoding: {
165+
alias: 'e',
166+
default: 'LINEAR16',
167+
global: true,
168+
requiresArg: true,
169+
type: 'string',
170+
},
171+
sampleRateHertz: {
172+
alias: 'r',
173+
default: 16000,
174+
global: true,
175+
requiresArg: true,
176+
type: 'number',
177+
},
178+
languageCode: {
179+
alias: 'l',
180+
default: 'en-US',
181+
global: true,
182+
requiresArg: true,
183+
type: 'string',
184+
},
185+
})
186+
.example(
187+
`node $0 sync-model ./resources/Google_Gnome.wav video -e LINEAR16 -r 16000`
188+
)
189+
.example(
190+
`node $0 sync-model-gcs gs://gcs-test-data/Google_Gnome.wav phone_call -e FLAC -r 16000`
191+
)
192+
.wrap(120)
193+
.recommendCommands()
194+
.epilogue(`For more information, see https://cloud.google.com/speech/docs`)
195+
.help()
196+
.strict().argv;

‎speech/resources/Google_Gnome.wav‎

1.7 MB
Binary file not shown.

‎speech/system-test/recognize.v1p1beta1.test.js‎

Lines changed: 59 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
1+
/**
2+
* Copyright 2016, Google, Inc.
3+
* Licensed under the Apache License, Version 2.0 (the "License");
4+
* you may not use this file except in compliance with the License.
5+
* You may obtain a copy of the License at
6+
*
7+
* http://www.apache.org/licenses/LICENSE-2.0
8+
*
9+
* Unless required by applicable law or agreed to in writing, software
10+
* distributed under the License is distributed on an "AS IS" BASIS,
11+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
* See the License for the specific language governing permissions and
13+
* limitations under the License.
14+
*/
15+
16+
'use strict';
17+
18+
const path = require(`path`);
19+
const storage = require(`@google-cloud/storage`)();
20+
const test = require(`ava`);
21+
const uuid = require(`uuid`);
22+
23+
const {runAsync} = require(`@google-cloud/nodejs-repo-tools`);
24+
25+
const bucketName = `nodejs-docs-samples-test-${uuid.v4()}`;
26+
const cmd = `node recognize.v1p1beta1.js`;
27+
const cwd = path.join(__dirname, `..`);
28+
const filename = `Google_Gnome.wav`;
29+
const filepath = path.join(__dirname, `../resources/${filename}`);
30+
const text = `the weather outside is sunny`;
31+
32+
test.before(async () => {
33+
const [bucket] = await storage.createBucket(bucketName);
34+
await bucket.upload(filepath);
35+
});
36+
37+
test.after.always(async () => {
38+
const bucket = storage.bucket(bucketName);
39+
await bucket.deleteFiles({force: true});
40+
await bucket.deleteFiles({force: true}); // Try a second time...
41+
await bucket.delete();
42+
});
43+
44+
test(`should run sync recognize with model selection`, async t => {
45+
const model = `video`;
46+
const output = await runAsync(`${cmd} sync-model ${filepath} ${model}`, cwd);
47+
t.true(output.includes(`Transcription:`));
48+
t.true(output.includes(text));
49+
});
50+
51+
test(`should run sync recognize on a GCS file with model selection`, async t => {
52+
const model = `video`;
53+
const output = await runAsync(
54+
`${cmd} sync-model-gcs gs://${bucketName}/${filename} ${model}`,
55+
cwd
56+
);
57+
t.true(output.includes(`Transcription:`));
58+
t.true(output.includes(text));
59+
});

0 commit comments

Comments
 (0)