Nodejs Google 语音 API 流停止
Nodejs Google Speech API Stream Stops
我从 https://github.com/GoogleCloudPlatform/nodejs-docs-samples/tree/master/speech (Requires auth with this 中提取了以下示例代码 (recognize.js)：
/**
* Copyright 2016, 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';
function syncRecognize (filename, encoding, sampleRate) {
// [START speech_sync_recognize]
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The path to the local file on which to perform speech recognition, e.g. /path/to/audio.raw
// const filename = '/path/to/audio.raw';
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
encoding: encoding,
sampleRate: sampleRate
};
// Detects speech in the audio file
speech.recognize(filename, request)
.then((results) => {
const transcription = results[0];
console.log(`Transcription: ${transcription}`);
});
// [END speech_sync_recognize]
}
function syncRecognizeGCS (gcsUri, encoding, sampleRate) {
// [START speech_sync_recognize_gcs]
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The Google Cloud Storage URI of the file on which to perform speech recognition, e.g. gs://my-bucket/audio.raw
// const gcsUri = 'gs://my-bucket/audio.raw';
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
encoding: encoding,
sampleRate: sampleRate
};
// Detects speech in the audio file
speech.recognize(gcsUri, request)
.then((results) => {
const transcription = results[0];
console.log(`Transcription: ${transcription}`);
});
// [END speech_sync_recognize_gcs]
}
function asyncRecognize (filename, encoding, sampleRate) {
// [START speech_async_recognize]
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The path to the local file on which to perform speech recognition, e.g. /path/to/audio.raw
// const filename = '/path/to/audio.raw';
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
encoding: encoding,
sampleRate: sampleRate
};
// Detects speech in the audio file. This creates a recognition job that you
// can wait for now, or get its result later.
speech.startRecognition(filename, request)
.then((results) => {
const operation = results[0];
// Get a Promise represention of the final result of the job
return operation.promise();
})
.then((transcription) => {
console.log(`Transcription: ${transcription}`);
});
// [END speech_async_recognize]
}
function asyncRecognizeGCS (gcsUri, encoding, sampleRate) {
// [START speech_async_recognize_gcs]
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The Google Cloud Storage URI of the file on which to perform speech recognition, e.g. gs://my-bucket/audio.raw
// const gcsUri = 'gs://my-bucket/audio.raw';
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
encoding: encoding,
sampleRate: sampleRate
};
// Detects speech in the audio file. This creates a recognition job that you
// can wait for now, or get its result later.
speech.startRecognition(gcsUri, request)
.then((results) => {
const operation = results[0];
// Get a Promise represention of the final result of the job
return operation.promise();
})
.then((transcription) => {
console.log(`Transcription: ${transcription}`);
});
// [END speech_async_recognize_gcs]
}
function streamingRecognize (filename, encoding, sampleRate) {
// [START speech_streaming_recognize]
const fs = require('fs');
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The path to the local file on which to perform speech recognition, e.g. /path/to/audio.raw
// const filename = '/path/to/audio.raw';
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
config: {
encoding: encoding,
sampleRate: sampleRate
}
};
// Stream the audio to the Google Cloud Speech API
const recognizeStream = speech.createRecognizeStream(request)
.on('error', console.error)
.on('data', (data) => {
console.log('Data received: %j', data);
});
// Stream an audio file from disk to the Speech API, e.g. "./resources/audio.raw"
fs.createReadStream(filename).pipe(recognizeStream);
// [END speech_streaming_recognize]
}
function streamingMicRecognize (encoding, sampleRate) {
// [START speech_streaming_mic_recognize]
const record = require('node-record-lpcm16');
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
config: {
encoding: encoding,
sampleRate: sampleRate
}
};
// Create a recognize stream
const recognizeStream = speech.createRecognizeStream(request)
.on('error', console.error)
.on('data', (data) => process.stdout.write(data.results));
// Start recording and send the microphone input to the Speech API
record.start({
sampleRate: sampleRate,
threshold: 0
}).pipe(recognizeStream);
console.log('Listening, press Ctrl+C to stop.');
// [END speech_streaming_mic_recognize]
}
require(`yargs`)
.demand(1)
.command(
`sync <filename>`,
`Detects speech in a local audio file.`,
{},
(opts) => syncRecognize(opts.filename, opts.encoding, opts.sampleRate)
)
.command(
`sync-gcs <gcsUri>`,
`Detects speech in an audio file located in a Google Cloud Storage bucket.`,
{},
(opts) => syncRecognizeGCS(opts.gcsUri, opts.encoding, opts.sampleRate)
)
.command(
`async <filename>`,
`Creates a job to detect speech in a local audio file, and waits for the job to complete.`,
{},
(opts) => asyncRecognize(opts.filename, opts.encoding, opts.sampleRate)
)
.command(
`async-gcs <gcsUri>`,
`Creates a job to detect speech in an audio file located in a Google Cloud Storage bucket, and waits for the job to complete.`,
{},
(opts) => asyncRecognizeGCS(opts.gcsUri, opts.encoding, opts.sampleRate)
)
.command(
`stream <filename>`,
`Detects speech in a local audio file by streaming it to the Speech API.`,
{},
(opts) => streamingRecognize(opts.filename, opts.encoding, opts.sampleRate)
)
.command(
`listen`,
`Detects speech in a microphone input stream.`,
{},
(opts) => streamingMicRecognize(opts.encoding, opts.sampleRate)
)
.options({
encoding: {
alias: 'e',
default: 'LINEAR16',
global: true,
requiresArg: true,
type: 'string'
},
sampleRate: {
alias: 'r',
default: 16000,
global: true,
requiresArg: true,
type: 'number'
}
})
.example(`node [=12=] sync ./resources/audio.raw -e LINEAR16 -r 16000`)
.example(`node [=12=] async-gcs gs://my-bucket/audio.raw -e LINEAR16 -r 16000`)
.example(`node [=12=] stream ./resources/audio.raw -e LINEAR16 -r 16000`)
.example(`node [=12=] listen`)
.wrap(120)
.recommendCommands()
.epilogue(`For more information, see https://cloud.google.com/speech/docs`)
.help()
.strict()
.argv;
我运行它与：节点recognize.js听
该示例最初有效。我对着我的麦克风说话，它会记录我对控制台说的话。问题是，如果我沉默几秒钟，它就会停止 listening/recognizing/printing。我一直在查看各种文件，但我不明白为什么。
我不是 100% 确定，但听起来可能有多种解释：
该请求要求“单一话语”(StreamingRecognitionConfig)
这似乎很不寻常，因为默认值似乎是 false。但是，在请求中明确表示无害 (const request = { singleUtterance: false, config: {...} })
您 运行 进入 client-defined 超时 (createRecognizeStream)。
这似乎也有点奇怪，因为我猜你不会坐在那里连续说了 60 秒然后说了这么长时间就停下来了。
您的麦克风正在关闭传播回语音客户端的流。
这似乎更合理一些，但我不是 100% 有信心。
如果您可以用麦克风录制您所说的内容并使用通过 createRecognizeStream 方法发送的文件（而不是实时音频流）重现此问题，则消除了最后一项，并且会使诊断更容易。
我从 https://github.com/GoogleCloudPlatform/nodejs-docs-samples/tree/master/speech (Requires auth with this 中提取了以下示例代码 (recognize.js)：
/**
* Copyright 2016, 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';
function syncRecognize (filename, encoding, sampleRate) {
// [START speech_sync_recognize]
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The path to the local file on which to perform speech recognition, e.g. /path/to/audio.raw
// const filename = '/path/to/audio.raw';
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
encoding: encoding,
sampleRate: sampleRate
};
// Detects speech in the audio file
speech.recognize(filename, request)
.then((results) => {
const transcription = results[0];
console.log(`Transcription: ${transcription}`);
});
// [END speech_sync_recognize]
}
function syncRecognizeGCS (gcsUri, encoding, sampleRate) {
// [START speech_sync_recognize_gcs]
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The Google Cloud Storage URI of the file on which to perform speech recognition, e.g. gs://my-bucket/audio.raw
// const gcsUri = 'gs://my-bucket/audio.raw';
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
encoding: encoding,
sampleRate: sampleRate
};
// Detects speech in the audio file
speech.recognize(gcsUri, request)
.then((results) => {
const transcription = results[0];
console.log(`Transcription: ${transcription}`);
});
// [END speech_sync_recognize_gcs]
}
function asyncRecognize (filename, encoding, sampleRate) {
// [START speech_async_recognize]
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The path to the local file on which to perform speech recognition, e.g. /path/to/audio.raw
// const filename = '/path/to/audio.raw';
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
encoding: encoding,
sampleRate: sampleRate
};
// Detects speech in the audio file. This creates a recognition job that you
// can wait for now, or get its result later.
speech.startRecognition(filename, request)
.then((results) => {
const operation = results[0];
// Get a Promise represention of the final result of the job
return operation.promise();
})
.then((transcription) => {
console.log(`Transcription: ${transcription}`);
});
// [END speech_async_recognize]
}
function asyncRecognizeGCS (gcsUri, encoding, sampleRate) {
// [START speech_async_recognize_gcs]
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The Google Cloud Storage URI of the file on which to perform speech recognition, e.g. gs://my-bucket/audio.raw
// const gcsUri = 'gs://my-bucket/audio.raw';
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
encoding: encoding,
sampleRate: sampleRate
};
// Detects speech in the audio file. This creates a recognition job that you
// can wait for now, or get its result later.
speech.startRecognition(gcsUri, request)
.then((results) => {
const operation = results[0];
// Get a Promise represention of the final result of the job
return operation.promise();
})
.then((transcription) => {
console.log(`Transcription: ${transcription}`);
});
// [END speech_async_recognize_gcs]
}
function streamingRecognize (filename, encoding, sampleRate) {
// [START speech_streaming_recognize]
const fs = require('fs');
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The path to the local file on which to perform speech recognition, e.g. /path/to/audio.raw
// const filename = '/path/to/audio.raw';
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
config: {
encoding: encoding,
sampleRate: sampleRate
}
};
// Stream the audio to the Google Cloud Speech API
const recognizeStream = speech.createRecognizeStream(request)
.on('error', console.error)
.on('data', (data) => {
console.log('Data received: %j', data);
});
// Stream an audio file from disk to the Speech API, e.g. "./resources/audio.raw"
fs.createReadStream(filename).pipe(recognizeStream);
// [END speech_streaming_recognize]
}
function streamingMicRecognize (encoding, sampleRate) {
// [START speech_streaming_mic_recognize]
const record = require('node-record-lpcm16');
// Imports the Google Cloud client library
const Speech = require('@google-cloud/speech');
// Instantiates a client
const speech = Speech();
// The encoding of the audio file, e.g. 'LINEAR16'
// const encoding = 'LINEAR16';
// The sample rate of the audio file, e.g. 16000
// const sampleRate = 16000;
const request = {
config: {
encoding: encoding,
sampleRate: sampleRate
}
};
// Create a recognize stream
const recognizeStream = speech.createRecognizeStream(request)
.on('error', console.error)
.on('data', (data) => process.stdout.write(data.results));
// Start recording and send the microphone input to the Speech API
record.start({
sampleRate: sampleRate,
threshold: 0
}).pipe(recognizeStream);
console.log('Listening, press Ctrl+C to stop.');
// [END speech_streaming_mic_recognize]
}
require(`yargs`)
.demand(1)
.command(
`sync <filename>`,
`Detects speech in a local audio file.`,
{},
(opts) => syncRecognize(opts.filename, opts.encoding, opts.sampleRate)
)
.command(
`sync-gcs <gcsUri>`,
`Detects speech in an audio file located in a Google Cloud Storage bucket.`,
{},
(opts) => syncRecognizeGCS(opts.gcsUri, opts.encoding, opts.sampleRate)
)
.command(
`async <filename>`,
`Creates a job to detect speech in a local audio file, and waits for the job to complete.`,
{},
(opts) => asyncRecognize(opts.filename, opts.encoding, opts.sampleRate)
)
.command(
`async-gcs <gcsUri>`,
`Creates a job to detect speech in an audio file located in a Google Cloud Storage bucket, and waits for the job to complete.`,
{},
(opts) => asyncRecognizeGCS(opts.gcsUri, opts.encoding, opts.sampleRate)
)
.command(
`stream <filename>`,
`Detects speech in a local audio file by streaming it to the Speech API.`,
{},
(opts) => streamingRecognize(opts.filename, opts.encoding, opts.sampleRate)
)
.command(
`listen`,
`Detects speech in a microphone input stream.`,
{},
(opts) => streamingMicRecognize(opts.encoding, opts.sampleRate)
)
.options({
encoding: {
alias: 'e',
default: 'LINEAR16',
global: true,
requiresArg: true,
type: 'string'
},
sampleRate: {
alias: 'r',
default: 16000,
global: true,
requiresArg: true,
type: 'number'
}
})
.example(`node [=12=] sync ./resources/audio.raw -e LINEAR16 -r 16000`)
.example(`node [=12=] async-gcs gs://my-bucket/audio.raw -e LINEAR16 -r 16000`)
.example(`node [=12=] stream ./resources/audio.raw -e LINEAR16 -r 16000`)
.example(`node [=12=] listen`)
.wrap(120)
.recommendCommands()
.epilogue(`For more information, see https://cloud.google.com/speech/docs`)
.help()
.strict()
.argv;
我运行它与：节点recognize.js听
该示例最初有效。我对着我的麦克风说话，它会记录我对控制台说的话。问题是，如果我沉默几秒钟，它就会停止 listening/recognizing/printing。我一直在查看各种文件，但我不明白为什么。
我不是 100% 确定，但听起来可能有多种解释：
该请求要求“单一话语”(StreamingRecognitionConfig)
这似乎很不寻常，因为默认值似乎是
false。但是，在请求中明确表示无害 (const request = { singleUtterance: false, config: {...} })您 运行 进入 client-defined 超时 (createRecognizeStream)。
这似乎也有点奇怪，因为我猜你不会坐在那里连续说了 60 秒然后说了这么长时间就停下来了。
您的麦克风正在关闭传播回语音客户端的流。
这似乎更合理一些，但我不是 100% 有信心。
如果您可以用麦克风录制您所说的内容并使用通过 createRecognizeStream 方法发送的文件（而不是实时音频流）重现此问题，则消除了最后一项，并且会使诊断更容易。