Я хотел бы понять это.
- Пользователь говорит с веб-браузером.
- Веб-браузер записывает свой голос в виде файла WAV (Recorder. js) и отправляет его на сервер (стандартная среда Google App Engine Python 3.7).
- Python сервер вызывает Google Cloud text в речь API, транскрибирует WAV-файл и отправляет транскрибированный текст в веб-браузер.
Я получил это сообщение об ошибке.
2020-01-30 08:37:38 speech[20200130t173543] "GET / HTTP/1.1" 200
2020-01-30 08:37:38 speech[20200130t173543] [2020-01-30 08:37:38 +0000] [8] [INFO] Starting gunicorn 20.0.4
2020-01-30 08:37:38 speech[20200130t173543] [2020-01-30 08:37:38 +0000] [8] [INFO] Listening at: http://0.0.0.0:8081 (8)
2020-01-30 08:37:38 speech[20200130t173543] [2020-01-30 08:37:38 +0000] [8] [INFO] Using worker: sync
2020-01-30 08:37:38 speech[20200130t173543] [2020-01-30 08:37:38 +0000] [15] [INFO] Booting worker with pid: 15
2020-01-30 08:37:55 speech[20200130t173543] "POST / HTTP/1.1" 500
2020-01-30 08:37:56 speech[20200130t173543] /tmp/file.wav exists
2020-01-30 08:37:56 speech[20200130t173543] [2020-01-30 08:37:56,717] ERROR in app: Exception on / [POST]
2020-01-30 08:37:56 speech[20200130t173543] Traceback (most recent call last):
File "/env/lib/python3.7/site-packages/google/api_core/grpc_helpers.py", line 57, in error_remapped_callable return callable_(*args, **kwargs)
File "/env/lib/python3.7/site-packages/grpc/_channel.py", line 824, in __call__ return _end_unary_response_blocking(state, call, False, None)
File "/env/lib/python3.7/site-packages/grpc/_channel.py", line 726, in _end_unary_response_blocking raise _InactiveRpcError(state) grpc._channel._InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
2020-01-30 08:37:56 speech[20200130t173543] status = StatusCode.INVALID_ARGUMENT
2020-01-30 08:37:56 speech[20200130t173543] details = "RecognitionAudio not set."
2020-01-30 08:37:56 speech[20200130t173543] debug_error_string = "{"created":"@1580373476.716586092","description":"Error received from peer ipv4:172.217.175.42:443","file":"src/core/lib/surface/call.cc","file_line":1056,"grpc_message":"RecognitionAudio not set.","grpc_status":3}"
2020-01-30 08:37:56 speech[20200130t173543] >
2020-01-30 08:37:56 speech[20200130t173543]
2020-01-30 08:37:56 speech[20200130t173543] The above exception was the direct cause of the following exception:
2020-01-30 08:37:56 speech[20200130t173543]
2020-01-30 08:37:57 speech[20200130t173543] Traceback (most recent call last):
File "/env/lib/python3.7/site-packages/flask/app.py", line 2446, in wsgi_app response = self.full_dispatch_request()
File "/env/lib/python3.7/site-packages/flask/app.py", line 1951, in full_dispatch_request rv = self.handle_user_exception(e)
File "/env/lib/python3.7/site-packages/flask/app.py", line 1820, in handle_user_exception reraise(exc_type, exc_value, tb)
File "/env/lib/python3.7/site-packages/flask/_compat.py", line 39, in reraise raise value
File "/env/lib/python3.7/site-packages/flask/app.py", line 1949, in full_dispatch_request rv = self.dispatch_request()
File "/env/lib/python3.7/site-packages/flask/app.py", line 1935, in dispatch_request return self.view_functions[rule.endpoint](**req.view_args)
File "/srv/main.py", line 38, in index response = client.recognize(config, audio)
File "/env/lib/python3.7/site-packages/google/cloud/speech_v1/gapic/speech_client.py", line 256, in recognize request, retry=retry, timeout=timeout, metadata=metadata
File "/env/lib/python3.7/site-packages/google/api_core/gapic_v1/method.py", line 143, in __call__ return wrapped_func(*args, **kwargs)
File "/env/lib/python3.7/site-packages/google/api_core/retry.py", line 286, in retry_wrapped_func on_error=on_error,
File "/env/lib/python3.7/site-packages/google/api_core/retry.py", line 184, in retry_target return target()
File "/env/lib/python3.7/site-packages/google/api_core/timeout.py", line 214, in func_with_timeout return func(*args, **kwargs)
File "/env/lib/python3.7/site-packages/google/api_core/grpc_helpers.py", line 59, in error_remapped_callable six.raise_from(exceptions.from_grpc_error(exc), exc)
File "<string>", line 3, in raise_from google.api_core.exceptions.InvalidArgument: 400 RecognitionAudio not set.
Я думал, что есть два проблемы. Первый - это.
2020-01-30 08:37:56 speech[20200130t173543] Traceback (most recent call last):
File "/env/lib/python3.7/site-packages/google/api_core/grpc_helpers.py", line 57, in error_remapped_callable return callable_(*args, **kwargs)
File "/env/lib/python3.7/site-packages/grpc/_channel.py", line 824, in __call__ return _end_unary_response_blocking(state, call, False, None)
File "/env/lib/python3.7/site-packages/grpc/_channel.py", line 726, in _end_unary_response_blocking raise _InactiveRpcError(state) grpc._channel._InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
Я искал "InactiveRpcError google cloud speech api", но не смог найти решение.
Второй - это.
2020-01-30 08:37:57 speech[20200130t173543] Traceback (most recent call last):
File "/env/lib/python3.7/site-packages/flask/app.py", line 2446, in wsgi_app response = self.full_dispatch_request()
File "/env/lib/python3.7/site-packages/flask/app.py", line 1951, in full_dispatch_request rv = self.handle_user_exception(e)
File "/env/lib/python3.7/site-packages/flask/app.py", line 1820, in handle_user_exception reraise(exc_type, exc_value, tb)
File "/env/lib/python3.7/site-packages/flask/_compat.py", line 39, in reraise raise value
File "/env/lib/python3.7/site-packages/flask/app.py", line 1949, in full_dispatch_request rv = self.dispatch_request()
File "/env/lib/python3.7/site-packages/flask/app.py", line 1935, in dispatch_request return self.view_functions[rule.endpoint](**req.view_args)
File "/srv/main.py", line 38, in index response = client.recognize(config, audio)
File "/env/lib/python3.7/site-packages/google/cloud/speech_v1/gapic/speech_client.py", line 256, in recognize request, retry=retry, timeout=timeout, metadata=metadata
File "/env/lib/python3.7/site-packages/google/api_core/gapic_v1/method.py", line 143, in __call__ return wrapped_func(*args, **kwargs)
File "/env/lib/python3.7/site-packages/google/api_core/retry.py", line 286, in retry_wrapped_func on_error=on_error,
File "/env/lib/python3.7/site-packages/google/api_core/retry.py", line 184, in retry_target return target()
File "/env/lib/python3.7/site-packages/google/api_core/timeout.py", line 214, in func_with_timeout return func(*args, **kwargs)
File "/env/lib/python3.7/site-packages/google/api_core/grpc_helpers.py", line 59, in error_remapped_callable six.raise_from(exceptions.from_grpc_error(exc), exc)
File "<string>", line 3, in raise_from google.api_core.exceptions.InvalidArgument: 400 RecognitionAudio not set.
Я искал "InvalidArgument: 400 RecognitionAudio not set". Я нашел решение изменить sample_rate_hertz = 16000. Итак, я изменил его на «48000», но получил ту же ошибку. Кроме того, я удалил sample_rate_hertz = 16000, но получил ту же ошибку.
Не могли бы вы дать мне какую-либо информацию или предложение?
Заранее спасибо.
С уважением, Казу
Моя структура каталогов здесь.
.
├── app.yaml
├── credentials.json
├── main.py
├── requirements.txt
├── static
│ └── js
│ └── app.js
└── templates
└── index.html
Это app.yaml.
runtime: python37
entrypoint: gunicorn -b :$PORT main:app
service: speech
Это main.py.
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from flask import Flask
from flask import request
from flask import render_template
from flask import send_file
from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types
import os
import io
app = Flask(__name__)
@app.route("/", methods=['POST', 'GET'])
def index():
if request.method == "POST":
f = open('/tmp/file.wav', 'wb')
f.write(request.data)
f.close()
if os.path.isfile('/tmp/file.wav'):
print("/tmp/file.wav exists")
os.environ["GOOGLE_APPLICATION_CREDENTIALS"]="credentials.json"
client = speech.SpeechClient()
# [START speech_python_migration_sync_request]
# [START speech_python_migration_config]
with io.open('/tmp/file.wav', 'rb') as audio_file:
content = audio_file.read()
audio = types.RecognitionAudio(content=content)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=16000,
language_code='ja-JP')
# [END speech_python_migration_config]
# [START speech_python_migration_sync_response]
response = client.recognize(config, audio)
# [END speech_python_migration_sync_request]
# Each result is for a consecutive portion of the audio. Iterate through
# them to get the transcripts for the entire audio file.
for result in response.results:
# The first alternative is the most likely one for this portion.
print(u'Transcript: {}'.format(result.alternatives[0].transcript))
return print(u'Transcript: {}'.format(result.alternatives[0].transcript))
else:
return render_template("index.html")
if __name__ == "__main__":
app.run()
Это файл require.txt.
Flask
google-cloud-speech
gunicorn
Это индекс. html.
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>Simple Recorder.js demo with record, stop and pause - addpipe.com</title>
<meta name="viewport" content="width=device-width, initial-scale=1.0">
</head>
<body>
<h1>Simple Recorder.js demo</h1>
<div id="controls">
<button id="recordButton">Record</button>
<button id="pauseButton" disabled>Pause</button>
<button id="stopButton" disabled>Stop</button>
</div>
<div id="formats">Format: start recording to see sample rate</div>
<p><strong>Recordings:</strong></p>
<ol id="recordingsList"></ol>
<!-- inserting these scripts at the end to be able to use all the elements in the DOM -->
<script src="https://cdn.rawgit.com/mattdiamond/Recorderjs/08e7abd9/dist/recorder.js"></script>
<script src="/static/js/app.js"></script>
</body>
</html>
Это приложение. js.
//webkitURL is deprecated but nevertheless
URL = window.URL || window.webkitURL;
var gumStream; //stream from getUserMedia()
var rec; //Recorder.js object
var input; //MediaStreamAudioSourceNode we'll be recording
// shim for AudioContext when it's not avb.
var AudioContext = window.AudioContext || window.webkitAudioContext;
var audioContext //audio context to help us record
var recordButton = document.getElementById("recordButton");
var stopButton = document.getElementById("stopButton");
var pauseButton = document.getElementById("pauseButton");
//add events to those 2 buttons
recordButton.addEventListener("click", startRecording);
stopButton.addEventListener("click", stopRecording);
pauseButton.addEventListener("click", pauseRecording);
function startRecording() {
console.log("recordButton clicked");
/*
Simple constraints object, for more advanced audio features see
https://addpipe.com/blog/audio-constraints-getusermedia/
*/
var constraints = { audio: true, video:false }
/*
Disable the record button until we get a success or fail from getUserMedia()
*/
recordButton.disabled = true;
stopButton.disabled = false;
pauseButton.disabled = false
/*
We're using the standard promise based getUserMedia()
https://developer.mozilla.org/en-US/docs/Web/API/MediaDevices/getUserMedia
*/
navigator.mediaDevices.getUserMedia(constraints).then(function(stream) {
console.log("getUserMedia() success, stream created, initializing Recorder.js ...");
/*
create an audio context after getUserMedia is called
sampleRate might change after getUserMedia is called, like it does on macOS when recording through AirPods
the sampleRate defaults to the one set in your OS for your playback device
*/
audioContext = new AudioContext();
//update the format
document.getElementById("formats").innerHTML="Format: 1 channel pcm @ "+audioContext.sampleRate/1000+"kHz"
/* assign to gumStream for later use */
gumStream = stream;
/* use the stream */
input = audioContext.createMediaStreamSource(stream);
/*
Create the Recorder object and configure to record mono sound (1 channel)
Recording 2 channels will double the file size
*/
rec = new Recorder(input,{numChannels:1})
//start the recording process
rec.record()
console.log("Recording started");
}).catch(function(err) {
//enable the record button if getUserMedia() fails
recordButton.disabled = false;
stopButton.disabled = true;
pauseButton.disabled = true
});
}
function pauseRecording(){
console.log("pauseButton clicked rec.recording=",rec.recording );
if (rec.recording){
//pause
rec.stop();
pauseButton.innerHTML="Resume";
}else{
//resume
rec.record()
pauseButton.innerHTML="Pause";
}
}
function stopRecording() {
console.log("stopButton clicked");
//disable the stop button, enable the record too allow for new recordings
stopButton.disabled = true;
recordButton.disabled = false;
pauseButton.disabled = true;
//reset button just in case the recording is stopped while paused
pauseButton.innerHTML="Pause";
//tell the recorder to stop the recording
rec.stop();
//stop microphone access
gumStream.getAudioTracks()[0].stop();
//create the wav blob and pass it on to createDownloadLink
rec.exportWAV(createDownloadLink);
}
function createDownloadLink(blob) {
var url = URL.createObjectURL(blob);
var au = document.createElement('audio');
var li = document.createElement('li');
var link = document.createElement('a');
//name of .wav file to use during upload and download (without extendion)
var filename = new Date().toISOString();
//add controls to the <audio> element
au.controls = true;
au.src = url;
//save to disk link
link.href = url;
link.download = filename+".wav"; //download forces the browser to donwload the file using the filename
link.innerHTML = "Save to disk";
//add the new audio element to li
li.appendChild(au);
//add the filename to the li
li.appendChild(document.createTextNode(filename+".wav "))
//add the save to disk link to li
li.appendChild(link);
//upload link
var upload = document.createElement('a');
upload.href="#";
upload.innerHTML = "Upload";
upload.addEventListener("click", function(event){
var xhr=new XMLHttpRequest();
xhr.onload=function(e) {
if(this.readyState === 4) {
console.log("Server returned: ",e.target.responseText);
}
};
var fd=new FormData();
fd.append("audio_data",blob, filename);
xhr.open("POST","/",true);
xhr.send(fd);
})
li.appendChild(document.createTextNode (" "))//add a space in between
li.appendChild(upload)//add the upload link to li
//add the li element to the ol
recordingsList.appendChild(li);
}