首页 > 代码库 > 百度语音识别REST API完整Demo

百度语音识别REST API完整Demo

2024-09-07 23:05:05   220人阅读

说明：web开发

原理：

  1、html5录制音频文件;

  2、将录制好的音频文件 通过 post 传给服务器

  3、服务器通过 百度语音识别 REST API 传给百度服务器，并返回文字

Demo文件：

  1、luyin.html

  2、luyin.js

  3、yuyin.php

以下是文件内容：

luyin.html

<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/xhtml">
<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /></head>
<body>
    <script type="text/javascript" src="luyin.js"></script>
    <div>
        <audio controls autoplay></audio>
        <input onclick="startRecording()" type="button" value="录音" />
        <input onclick="stopRecording()" type="button" value="停止" />
        <input onclick="playRecording()" type="button" value="播放" />
        <input onclick="uploadAudio()" type="button" value="提交" />
    </div>
    <script>
        var recorder;
        var audio = document.querySelector(‘audio‘);
        function startRecording() {
            HZRecorder.get(function (rec) {
                recorder = rec;
                recorder.start();
            });
        }
        function stopRecording() {
            recorder.stop();
        }
        function playRecording() {
            recorder.play(audio);
        }
        function uploadAudio() {
            
            //提交到服务器
            recorder.upload("sample_1.php", function (state, e) {
                switch (state) {
                    case ‘uploading‘:
                        //var percentComplete = Math.round(e.loaded * 100 / e.total) + ‘%‘;
                        break;
                    case ‘ok‘:
                        //alert(e.target.responseText);
                        alert("上传成功");
                        break;
                    case ‘error‘:
                        alert("上传失败");
                        break;
                    case ‘cancel‘:
                        alert("上传被取消");
                        break;
                }
            });
        }
    </script>
</body>
</html>

luyin.js

(function (window) {
    //兼容
    window.URL = window.URL || window.webkitURL;
    navigator.getUserMedia = navigator.getUserMedia || navigator.webkitGetUserMedia || navigator.mozGetUserMedia || navigator.msGetUserMedia;

    var HZRecorder = function (stream, config) {
        config = config || {};
        config.sampleBits = config.sampleBits || 16;      //采样数位 8, 16
        config.sampleRate = config.sampleRate || (16000);   //采样率(1/6 44100)

        var context = new (window.webkitAudioContext || window.AudioContext)();
        var audioInput = context.createMediaStreamSource(stream);
        var createScript = context.createScriptProcessor || context.createJavaScriptNode;
        var recorder = createScript.apply(context, [4096, 1, 1]);

        var audioData =http://www.mamicode.com/ {
            size: 0          //录音文件长度
            , buffer: []     //录音缓存
            , inputSampleRate: context.sampleRate    //输入采样率
            , inputSampleBits: 16       //输入采样数位 8, 16
            , outputSampleRate: config.sampleRate    //输出采样率
            , oututSampleBits: config.sampleBits       //输出采样数位 8, 16
            , input: function (data) {
                this.buffer.push(new Float32Array(data));
                this.size += data.length;
            }
            , compress: function () { //合并压缩
                //合并
                var data = http://www.mamicode.com/new Float32Array(this.size);
                var offset = 0;
                for (var i = 0; i < this.buffer.length; i++) {
                    data.set(this.buffer[i], offset);
                    offset += this.buffer[i].length;
                }
                //压缩
                var compression = parseInt(this.inputSampleRate / this.outputSampleRate);
                var length = data.length / compression;
                var result = new Float32Array(length);
                var index = 0, j = 0;
                while (index < length) {
                    result[index] = data[j];
                    j += compression;
                    index++;
                }
                return result;
            }
            , encodeWAV: function () {
                var sampleRate = Math.min(this.inputSampleRate, this.outputSampleRate);
                var sampleBits = Math.min(this.inputSampleBits, this.oututSampleBits);
                var bytes = this.compress();
                var dataLength = bytes.length * (sampleBits / 8);
                var buffer = new ArrayBuffer(44 + dataLength);
                var data = http://www.mamicode.com/new DataView(buffer);

                var channelCount = 1;//单声道
                var offset = 0;

                var writeString = function (str) {
                    for (var i = 0; i < str.length; i++) {
                        data.setUint8(offset + i, str.charCodeAt(i));
                    }
                }

                // 资源交换文件标识符 
                writeString(‘RIFF‘); offset += 4;
                // 下个地址开始到文件尾总字节数,即文件大小-8 
                data.setUint32(offset, 36 + dataLength, true); offset += 4;
                // WAV文件标志
                writeString(‘WAVE‘); offset += 4;
                // 波形格式标志 
                writeString(‘fmt ‘); offset += 4;
                // 过滤字节,一般为 0x10 = 16 
                data.setUint32(offset, 16, true); offset += 4;
                // 格式类别 (PCM形式采样数据) 
                data.setUint16(offset, 1, true); offset += 2;
                // 通道数 
                data.setUint16(offset, channelCount, true); offset += 2;
                // 采样率,每秒样本数,表示每个通道的播放速度 
                data.setUint32(offset, sampleRate, true); offset += 4;
                // 波形数据传输率 (每秒平均字节数) 单声道×每秒数据位数×每样本数据位/8 
                data.setUint32(offset, channelCount * sampleRate * (sampleBits / 8), true); offset += 4;
                // 快数据调整数 采样一次占用字节数 单声道×每样本的数据位数/8 
                data.setUint16(offset, channelCount * (sampleBits / 8), true); offset += 2;
                // 每样本数据位数 
                data.setUint16(offset, sampleBits, true); offset += 2;
                // 数据标识符 
                writeString(‘data‘); offset += 4;
                // 采样数据总数,即数据总大小-44 
                data.setUint32(offset, dataLength, true); offset += 4;
                // 写入采样数据 
                if (sampleBits === 8) {
                    for (var i = 0; i < bytes.length; i++, offset++) {
                        var s = Math.max(-1, Math.min(1, bytes[i]));
                        var val = s < 0 ? s * 0x8000 : s * 0x7FFF;
                        val = parseInt(255 / (65535 / (val + 32768)));
                        data.setInt8(offset, val, true);
                    }
                } else {
                    for (var i = 0; i < bytes.length; i++, offset += 2) {
                        var s = Math.max(-1, Math.min(1, bytes[i]));
                        data.setInt16(offset, s < 0 ? s * 0x8000 : s * 0x7FFF, true);
                    }
                }

                return new Blob([data], { type: ‘audio/wav‘ });
            }
        };

        //开始录音
        this.start = function () {
            audioInput.connect(recorder);
            recorder.connect(context.destination);
        }

        //停止
        this.stop = function () {
            recorder.disconnect();
        }

        //获取音频文件
        this.getBlob = function () {
            this.stop();
            return audioData.encodeWAV();
        }

        //回放
        this.play = function (audio) {
            audio.src = window.URL.createObjectURL(this.getBlob());
        }

        //上传
        this.upload = function (url, callback) {
            var fd = new FormData();
            fd.append("audioData", this.getBlob());
            var xhr = new XMLHttpRequest();
            if (callback) {
                xhr.upload.addEventListener("progress", function (e) {
                    callback(‘uploading‘, e);
                }, false);
                xhr.addEventListener("load", function (e) {
                    callback(‘ok‘, e);
                }, false);
                xhr.addEventListener("error", function (e) {
                    callback(‘error‘, e);
                }, false);
                xhr.addEventListener("abort", function (e) {
                    callback(‘cancel‘, e);
                }, false);
            }
            xhr.open("POST", url);
            xhr.send(fd);
        }

        //音频采集
        recorder.onaudioprocess = function (e) {
            audioData.input(e.inputBuffer.getChannelData(0));
            //record(e.inputBuffer.getChannelData(0));
        }

    };
    //抛出异常
    HZRecorder.throwError = function (message) {
        alert(message);
        throw new function () { this.toString = function () { return message; } }
    }
    //是否支持录音
    HZRecorder.canRecording = (navigator.getUserMedia != null);
    //获取录音机
    HZRecorder.get = function (callback, config) {
        if (callback) {
            if (navigator.getUserMedia) {
                navigator.getUserMedia(
                    { audio: true } //只启用音频
                    , function (stream) {
                        var rec = new HZRecorder(stream, config);
                        callback(rec);
                    }
                    , function (error) {
                        switch (error.code || error.name) {
                            case ‘PERMISSION_DENIED‘:
                            case ‘PermissionDeniedError‘:
                                HZRecorder.throwError(‘用户拒绝提供信息。‘);
                                break;
                            case ‘NOT_SUPPORTED_ERROR‘:
                            case ‘NotSupportedError‘:
                                HZRecorder.throwError(‘浏览器不支持硬件设备。‘);
                                break;
                            case ‘MANDATORY_UNSATISFIED_ERROR‘:
                            case ‘MandatoryUnsatisfiedError‘:
                                HZRecorder.throwError(‘无法发现指定的硬件设备。‘);
                                break;
                            default:
                                HZRecorder.throwError(‘无法打开麦克风。异常信息:‘ + (error.code || error.name));
                                break;
                        }
                    });
            } else {
                HZRecorder.throwErr(‘当前浏览器不支持录音功能。‘); return;
            }
        }
    }

    window.HZRecorder = HZRecorder;

})(window);

yuyin.php 

<?php
define(‘AUDIO_FILE‘, $_FILES[‘audioData‘][‘tmp_name‘]);
//define(‘AUDIO_FILE‘, "./test.pcm");
$url = "http://vop.baidu.com/server_api";

//填写参数
$cuid = "";            //用户 ID，推荐使用设备mac 地址/手机IMEI 等设备唯一性参数
$apiKey = "";        //百度的 API Key
$secretKey = "";    //百度的 Secret Key

$auth_url = "http://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id=".$apiKey."&client_secret=".$secretKey;
//用 https 访问 报证书错误问题
//$auth_url = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id=".$apiKey."&client_secret=".$secretKey;
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $auth_url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 5);
$response = curl_exec($ch);
if(curl_errno($ch))
{
    print curl_error($ch);
}
curl_close($ch);
$response = json_decode($response, true);
$token = $response[‘access_token‘];

$audio = file_get_contents(AUDIO_FILE);
$base_data = base64_encode($audio);
$array = array(
        "format" => "pcm",
        "rate" => 8000,
        "channel" => 1,
        //"lan" => "zh",
        "token" => $token,
        "cuid"=> $cuid,
        //"url" => "http://www.xxx.com/sample.pcm",
        //"callback" => "http://www.xxx.com/audio/callback",
        "len" => filesize(AUDIO_FILE),
        "speech" => $base_data,
        );
$json_array = json_encode($array);
$content_len = "Content-Length: ".strlen($json_array);
$header = array ($content_len, ‘Content-Type: application/json; charset=utf-8‘);

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 30);
curl_setopt($ch, CURLOPT_TIMEOUT, 30);
curl_setopt($ch, CURLOPT_POSTFIELDS, $json_array);
$response = curl_exec($ch);
if(curl_errno($ch))
{
    print curl_error($ch);
}
curl_close($ch);
echo $response;
$response = json_decode($response, true);
var_dump($response);

?>

 

百度语音识别REST API完整Demo


联系
我们