话不多说，直接怼代码，有不懂的，可以留言
简单的实现，前后端的语音交互。
import os
from uuid import uuid4
from aip import AipSpeech
from aip import AipNlp import settings """ 你的 APPID AK SK """
APP_ID = ''
API_KEY = 'KqqpO9GclBimrcSNrSANPhUQ'
SECRET_KEY = 'xc7IFW4w6DVtuNQlMkBX05Ulhx5Mm5zh' client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
nlp_client = AipNlp(APP_ID, API_KEY, SECRET_KEY) # 音频转为文本
def audio2text(file_name):
file_path = os.path.join(settings.AUDIO_PCM_DIR, file_name)
cmd_str = f'ffmpeg -y -i {file_path} -acodec pcm_s16le -f s16le -ac 1 -ar 16000 {file_path}.pcm'
os.system(cmd_str)
with open(f'{file_path}.pcm', 'rb') as f:
audio_context = f.read()
res = client.asr(audio_context, 'pcm', 16000, {
"dev_pid": 1537
})
print("res",res)
if res.get('err_no'):
return res
return res.get('result')[0] # 文本转为音频
def text2audio(text):
file_name = f"{uuid4()}.mp3"
file_path = os.path.join(settings.AUDIO_DIR, file_name)
res = client.synthesis(text, 'zh', 1, {
"vol": 5,
'pit': 7,
"spd": 4,
"per": 4
})
if isinstance(res, dict):
return res
with open(file_path, 'wb') as f:
f.write(res)
return file_name # 词法的匹配分析
def my_nlp(text):
print("text", nlp_client.simnet('你今年几岁了', text))
if nlp_client.simnet('你今年几岁了', text).get('score') >= 0.72:
return '我今年73了，不然84也行'
elif nlp_client.simnet('你叫什么名字', text).get('score') >= 0.72:
return '我的名字叫傻逼'
elif nlp_client.simnet('你在哪儿学习',text).get('score') >= 0.72:
return '我在老男孩教育'
else:
return '不知道你在说什么'
封装百度的AI接口
html页面
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Title</title>
</head>
<body>
<audio autoplay="autoplay"
controls id="play_mp3"
src="http://127.0.0.1:5000/getfile/ad74226f-3646-40d5-9548-7e817f1cb405.mp3">
浏览器不支持
</audio>
<button onclick="start_reco()">开始录音</button>
<button onclick="stop_reco()">结束录音</button>
</body>
<script type="text/javascript" src="/static/Recorder.js"></script>
<script type="text/javascript">
//建立 websocket 连接
var ws = new WebSocket('ws://127.0.0.1:5000/upload');
// ws.onopen = function () {
// ws.send("hello")
// }; // 如何录音
var reco = null;
// 创建一个录音audiocontext对象
var audio_context = new AudioContext();
// 解决浏览器的兼容问题
navigator.getUserMedia = (navigator.getUserMedia ||
navigator.webkitGetUserMedia ||
navigator.mozGetUserMedia ||
navigator.msGetUserMedia); navigator.getUserMedia({audio:true},create_stream,function (err) {
console.log(err)
}); function create_stream(stream) {
var stream_input = audio_context.createMediaStreamSource(stream);
reco = new Recorder(stream_input)
}
// 开始录音
function start_reco() {
reco.record();
}
// 结束录音
function stop_reco() {
reco.stop();
get_audio();
reco.clear();
}
// 向后端发送录制的音频
function get_audio() {
reco.exportWAV(function (wav_file) {
ws.send(wav_file)
})
}
// 接收后端发送的信息，触发回调函数
ws.onmessage = function (ev) {
// 从ev.data中获取参数
var data = JSON.parse(ev.data);
document.getElementById("play_mp3").src = "http://127.0.0.1:5000/getfile/"+data.filename;
} </script>
</html>
后端flask 实现逻辑
import os
import json
from uuid import uuid4 from geventwebsocket.handler import WebSocketHandler
from geventwebsocket.websocket import WebSocket
from gevent.pywsgi import WSGIServer
from flask import Flask,request,render_template,send_file
import baidu_aip
import settings app = Flask(__name__) # type:Flask @app.route('/index')
def index():
return render_template('index.html') @app.route('/getfile/<filename>')
def getfile(filename):
file_path = os.path.join(settings.AUDIO_DIR,filename)
return send_file(file_path) @app.route('/upload')
def upload():
ws = request.environ.get('wsgi.websocket')
if not ws:
return '请使用websocket连接' while True:
message = ws.receive()
if isinstance(message,bytearray):
# if message:
file_name = f"{uuid4()}.wav"
file_path = os.path.join(settings.AUDIO_PCM_DIR,file_name)
with open(file_path,'wb') as f:
f.write(message)
asr_str = baidu_aip.audio2text(file_name)
answer = baidu_aip.my_nlp(asr_str)
file_mp3_name = baidu_aip.text2audio(answer)
send_dic = json.dumps({
"filename":file_mp3_name,
"play_type":'audio',
"sendtime":111
})
ws.send(send_dic)
else:
ws.close() if __name__ == '__main__':
http_server = WSGIServer(('127.0.0.1',5000),app,handler_class=WebSocketHandler)
http_server.serve_forever()
附上Recorder.js源码
(function(f){if(typeof exports==="object"&&typeof module!=="undefined"){module.exports=f()}else if(typeof define==="function"&&define.amd){define([],f)}else{var g;if(typeof window!=="undefined"){g=window}else if(typeof global!=="undefined"){g=global}else if(typeof self!=="undefined"){g=self}else{g=this}g.Recorder = f()}})(function(){var define,module,exports;return (function e(t,n,r){function s(o,u){if(!n[o]){if(!t[o]){var a=typeof require=="function"&&require;if(!u&&a)return a(o,!0);if(i)return i(o,!0);var f=new Error("Cannot find module '"+o+"'");throw f.code="MODULE_NOT_FOUND",f}var l=n[o]={exports:{}};t[o][0].call(l.exports,function(e){var n=t[o][1][e];return s(n?n:e)},l,l.exports,e,t,n,r)}return n[o].exports}var i=typeof require=="function"&&require;for(var o=0;o<r.length;o++)s(r[o]);return s})({1:[function(require,module,exports){
"use strict";
module.exports = require("./recorder").Recorder;
},{"./recorder":2}],2:[function(require,module,exports){
'use strict';
var _createClass = (function () {
function defineProperties(target, props) {
for (var i = 0; i < props.length; i++) {
var descriptor = props[i];descriptor.enumerable = descriptor.enumerable || false;descriptor.configurable = true;if ("value" in descriptor) descriptor.writable = true;Object.defineProperty(target, descriptor.key, descriptor);
}
}return function (Constructor, protoProps, staticProps) {
if (protoProps) defineProperties(Constructor.prototype, protoProps);if (staticProps) defineProperties(Constructor, staticProps);return Constructor;
};
})();
Object.defineProperty(exports, "__esModule", {
value: true
});
exports.Recorder = undefined;
var _inlineWorker = require('inline-worker');
var _inlineWorker2 = _interopRequireDefault(_inlineWorker);
function _interopRequireDefault(obj) {
return obj && obj.__esModule ? obj : { default: obj };
}
function _classCallCheck(instance, Constructor) {
if (!(instance instanceof Constructor)) {
throw new TypeError("Cannot call a class as a function");
}
}
var Recorder = exports.Recorder = (function () {
function Recorder(source, cfg) {
var _this = this;
_classCallCheck(this, Recorder);
this.config = {
bufferLen: 4096,
numChannels: 2,
mimeType: 'audio_pcm/wav'
};
this.recording = false;
this.callbacks = {
getBuffer: [],
exportWAV: []
};
Object.assign(this.config, cfg);
this.context = source.context;
this.node = (this.context.createScriptProcessor || this.context.createJavaScriptNode).call(this.context, this.config.bufferLen, this.config.numChannels, this.config.numChannels);
this.node.onaudioprocess = function (e) {
if (!_this.recording) return;
var buffer = [];
for (var channel = 0; channel < _this.config.numChannels; channel++) {
buffer.push(e.inputBuffer.getChannelData(channel));
}
_this.worker.postMessage({
command: 'record',
buffer: buffer
});
};
source.connect(this.node);
this.node.connect(this.context.destination); //this should not be necessary
var self = {};
this.worker = new _inlineWorker2.default(function () {
var recLength = 0,
recBuffers = [],
sampleRate = undefined,
numChannels = undefined;
self.onmessage = function (e) {
switch (e.data.command) {
case 'init':
init(e.data.config);
break;
case 'record':
record(e.data.buffer);
break;
case 'exportWAV':
exportWAV(e.data.type);
break;
case 'getBuffer':
getBuffer();
break;
case 'clear':
clear();
break;
}
};
function init(config) {
sampleRate = config.sampleRate;
numChannels = config.numChannels;
initBuffers();
}
function record(inputBuffer) {
for (var channel = 0; channel < numChannels; channel++) {
recBuffers[channel].push(inputBuffer[channel]);
}
recLength += inputBuffer[0].length;
}
function exportWAV(type) {
var buffers = [];
for (var channel = 0; channel < numChannels; channel++) {
buffers.push(mergeBuffers(recBuffers[channel], recLength));
}
var interleaved = undefined;
if (numChannels === 2) {
interleaved = interleave(buffers[0], buffers[1]);
} else {
interleaved = buffers[0];
}
var dataview = encodeWAV(interleaved);
var audioBlob = new Blob([dataview], { type: type });
self.postMessage({ command: 'exportWAV', data: audioBlob });
}
function getBuffer() {
var buffers = [];
for (var channel = 0; channel < numChannels; channel++) {
buffers.push(mergeBuffers(recBuffers[channel], recLength));
}
self.postMessage({ command: 'getBuffer', data: buffers });
}
function clear() {
recLength = 0;
recBuffers = [];
initBuffers();
}
function initBuffers() {
for (var channel = 0; channel < numChannels; channel++) {
recBuffers[channel] = [];
}
}
function mergeBuffers(recBuffers, recLength) {
var result = new Float32Array(recLength);
var offset = 0;
for (var i = 0; i < recBuffers.length; i++) {
result.set(recBuffers[i], offset);
offset += recBuffers[i].length;
}
return result;
}
function interleave(inputL, inputR) {
var length = inputL.length + inputR.length;
var result = new Float32Array(length);
var index = 0,
inputIndex = 0;
while (index < length) {
result[index++] = inputL[inputIndex];
result[index++] = inputR[inputIndex];
inputIndex++;
}
return result;
}
function floatTo16BitPCM(output, offset, input) {
for (var i = 0; i < input.length; i++, offset += 2) {
var s = Math.max(-1, Math.min(1, input[i]));
output.setInt16(offset, s < 0 ? s * 0x8000 : s * 0x7FFF, true);
}
}
function writeString(view, offset, string) {
for (var i = 0; i < string.length; i++) {
view.setUint8(offset + i, string.charCodeAt(i));
}
}
function encodeWAV(samples) {
var buffer = new ArrayBuffer(44 + samples.length * 2);
var view = new DataView(buffer);
/* RIFF identifier */
writeString(view, 0, 'RIFF');
/* RIFF chunk length */
view.setUint32(4, 36 + samples.length * 2, true);
/* RIFF type */
writeString(view, 8, 'WAVE');
/* format chunk identifier */
writeString(view, 12, 'fmt ');
/* format chunk length */
view.setUint32(16, 16, true);
/* sample format (raw) */
view.setUint16(20, 1, true);
/* channel count */
view.setUint16(22, numChannels, true);
/* sample rate */
view.setUint32(24, sampleRate, true);
/* byte rate (sample rate * block align) */
view.setUint32(28, sampleRate * 4, true);
/* block align (channel count * bytes per sample) */
view.setUint16(32, numChannels * 2, true);
/* bits per sample */
view.setUint16(34, 16, true);
/* data chunk identifier */
writeString(view, 36, 'data');
/* data chunk length */
view.setUint32(40, samples.length * 2, true);
floatTo16BitPCM(view, 44, samples);
return view;
}
}, self);
this.worker.postMessage({
command: 'init',
config: {
sampleRate: this.context.sampleRate,
numChannels: this.config.numChannels
}
});
this.worker.onmessage = function (e) {
var cb = _this.callbacks[e.data.command].pop();
if (typeof cb == 'function') {
cb(e.data.data);
}
};
}
_createClass(Recorder, [{
key: 'record',
value: function record() {
this.recording = true;
}
}, {
key: 'stop',
value: function stop() {
this.recording = false;
}
}, {
key: 'clear',
value: function clear() {
this.worker.postMessage({ command: 'clear' });
}
}, {
key: 'getBuffer',
value: function getBuffer(cb) {
cb = cb || this.config.callback;
if (!cb) throw new Error('Callback not set');
this.callbacks.getBuffer.push(cb);
this.worker.postMessage({ command: 'getBuffer' });
}
}, {
key: 'exportWAV',
value: function exportWAV(cb, mimeType) {
mimeType = mimeType || this.config.mimeType;
cb = cb || this.config.callback;
if (!cb) throw new Error('Callback not set');
this.callbacks.exportWAV.push(cb);
this.worker.postMessage({
command: 'exportWAV',
type: mimeType
});
}
}], [{
key: 'forceDownload',
value: function forceDownload(blob, filename) {
var url = (window.URL || window.webkitURL).createObjectURL(blob);
var link = window.document.createElement('a');
link.href = url;
link.download = filename || 'output.wav';
var click = document.createEvent("Event");
click.initEvent("click", true, true);
link.dispatchEvent(click);
}
}]);
return Recorder;
})();
exports.default = Recorder;
},{"inline-worker":3}],3:[function(require,module,exports){
"use strict";
module.exports = require("./inline-worker");
},{"./inline-worker":4}],4:[function(require,module,exports){
(function (global){
"use strict";
var _createClass = (function () { function defineProperties(target, props) { for (var key in props) { var prop = props[key]; prop.configurable = true; if (prop.value) prop.writable = true; } Object.defineProperties(target, props); } return function (Constructor, protoProps, staticProps) { if (protoProps) defineProperties(Constructor.prototype, protoProps); if (staticProps) defineProperties(Constructor, staticProps); return Constructor; }; })();
var _classCallCheck = function (instance, Constructor) { if (!(instance instanceof Constructor)) { throw new TypeError("Cannot call a class as a function"); } };
var WORKER_ENABLED = !!(global === global.window && global.URL && global.Blob && global.Worker);
var InlineWorker = (function () {
function InlineWorker(func, self) {
var _this = this;
_classCallCheck(this, InlineWorker);
if (WORKER_ENABLED) {
var functionBody = func.toString().trim().match(/^function\s*\w*\s*\([\w\s,]*\)\s*{([\w\W]*?)}$/)[1];
var url = global.URL.createObjectURL(new global.Blob([functionBody], { type: "text/javascript" }));
return new global.Worker(url);
}
this.self = self;
this.self.postMessage = function (data) {
setTimeout(function () {
_this.onmessage({ data: data });
}, 0);
};
setTimeout(function () {
func.call(self);
}, 0);
}
_createClass(InlineWorker, {
postMessage: {
value: function postMessage(data) {
var _this = this;
setTimeout(function () {
_this.self.onmessage({ data: data });
}, 0);
}
}
});
return InlineWorker;
})();
module.exports = InlineWorker;
}).call(this,typeof global !== "undefined" ? global : typeof self !== "undefined" ? self : typeof window !== "undefined" ? window : {})
},{}]},{},[1])(1)
});