百度语音解析项目 学习笔记(只看了前端)

it2025-04-14  5

html5录音+百度语音实现语音识别 学习了一下这位大佬的代码,顺手整理了一下方便调试。 确实可以实现。之前看了好多版本,录音问题不大,但是百度不认。 但是觉得文件有点大,希望能压缩。有空再研究一下。

<!DOCTYPE html> <html xmlns="http://www.w3.org/1999/xhtml"> <head> <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <title></title> </head> <body> <div> <audio controls autoplay></audio> <section id="content"></section> <p> <button id="startBtn" onclick="startRecording()">录音</button> <button id="stopBtn" onclick="stopRecording()" disabled>停止</button> <button id="playBtn" onclick="playRecording()" disabled>播放</button> <button id="uploadBtn" onclick="uploadAudio()" disabled>提交</button> </p> </div> <script type="text/javascript" src="HZRecorder.js"></script> <script> var audio = document.querySelector('audio'); var uploadUrl = "https://www.jerryjin.com/baiduyuyin"; // 服务端接口 var config = { sampleBits : 16, // 采样数位 sampleRate : 16000, // 采样率 channelCount : 1, // 单声道 fileName : Date.now() + '.wav' // 音频文件名 } // 点击事件 function startRecording(e) { console.log('点击开始'); HZRecorder.get(function (rec) { recorder = rec; recorder.start(); }, config); // 按钮状态 startBtn.disabled = true; stopBtn.disabled = false; playBtn.disabled = true; uploadBtn.disabled = true; } function stopRecording(e) { console.log('点击停止'); recorder.stop(); // 按钮状态 startBtn.disabled = false; stopBtn.disabled = true; playBtn.disabled = false; uploadBtn.disabled = false; } function playRecording(e) { console.log('点击播放'); recorder.play(audio); } function uploadAudio(e) { console.log('点击提交'); recorder.upload(uploadUrl, function (state, e) { switch (state) { case 'uploading': var percentComplete = Math.round(e.loaded * 100 / e.total) + '%'; break; case 'ok': console.log(e.target.response); var ele_p = document.createElement('p'); ele_p.innerText = e.target.response.data; content.appendChild(ele_p); break; case 'error': alert("上传失败"); break; case 'cancel': alert("上传被取消"); break; } }); } </script> </body> </html> (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) { console.log('HZRecorder 初始化'); 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 channelCount = config.channelCount || 1; // 单声道 var fileName = config.fileName || Date.now() + '.wav'; // 使用此文件名上传 var context = new AudioContext(); var audioInput = context.createMediaStreamSource(stream); var recorder = context.createScriptProcessor(4096, 1, 1); var audioData = { 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 = 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 = new DataView(buffer); 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(); var wavFile = new File([this.getBlob()], fileName, { type: 'audio/wav' }); // 封装成 file 对象,添加文件名 fd.append("file", wavFile); 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.responseType = 'json'; 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) { console.log('获取录音机'); 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或没有权限。 chrome47 以上要 https。测试的话在 127.0.0.1 下可以 http'); return; } } } window.HZRecorder = HZRecorder; })(window);
最新回复(0)