最近终于有一点时间抽空来看看最近的新技术，然后发现了苹果在去年出的新框架，可以直接语音转文字，简直厉害了，直接完爆了某些大公司。但是缺点在于只支持iOS10以上的系统，但是也算是一大进步，赞一个。
一、开发环境要求
XCode8以上,只有它之后的编译器里才有Speech.framework
二、创建工程开发
1.导入Speech.framework【Build Phases->Link Binary With Libraries->+】
2.info.plist文件中添加
Privacy - Speech Recognition Usage Description
使用语音识别
Privacy - Microphone Usage Description
使用麦克风
3.第一种：识别本地录音
#import "ViewController.h"#import
@interface ViewController ()
@property (nonatomic ,strong) SFSpeechRecognitionTask *recognitionTask;
@property (nonatomic ,strong) SFSpeechRecognizer *speechRecognizer;
@property (nonatomic ,strong) UILabel *recognizerLabel;
@end
@implementation ViewController
- (void)dealloc {
[self.recognitionTask cancel];
self.recognitionTask = nil;
}
- (void)viewDidLoad {
[super viewDidLoad];
self.view.backgroundColor = [UIColor whiteColor];
//0.0获取权限
[SFSpeechRecognizer requestAuthorization:^(SFSpeechRecognizerAuthorizationStatus status) {
switch (status) {
case SFSpeechRecognizerAuthorizationStatusNotDetermined:
break;
case SFSpeechRecognizerAuthorizationStatusDenied:
break;
case SFSpeechRecognizerAuthorizationStatusRestricted:
break;
case SFSpeechRecognizerAuthorizationStatusAuthorized:
break;
default:
break;
}
}];
//1.创建SFSpeechRecognizer识别实例
self.speechRecognizer = [[SFSpeechRecognizer alloc] initWithLocale:[[NSLocale alloc] initWithLocaleIdentifier:@"zh_CN"]];//中文识别
//@"zh"在iOS9之后就不是简体中文了，而是TW繁体中文
// [SFSpeechRecognizer supportedLocales];//根据手机设置的语言识别
// for (NSLocale *lacal in [SFSpeechRecognizer supportedLocales].allObjects) {
// NSLog(@"countryCode:%@ languageCode:%@ ", lacal.countryCode, lacal.languageCode);
// }
//2.创建识别请求
SFSpeechURLRecognitionRequest *request = [[SFSpeechURLRecognitionRequest alloc] initWithURL:[NSURL fileURLWithPath:[[NSBundle mainBundle] pathForResource:@"1122334455.mp3" ofType:nil]]];
//3.开始识别任务
self.recognitionTask = [self recognitionTaskWithRequest1:request];
}
- (SFSpeechRecognitionTask *)recognitionTaskWithRequest0:(SFSpeechURLRecognitionRequest *)request{
return [self.speechRecognizer recognitionTaskWithRequest:request resultHandler:^(SFSpeechRecognitionResult * _Nullable result, NSError * _Nullable error) {
if (!error) {
NSLog(@"语音识别解析正确--%@", result.bestTranscription.formattedString);
}else {
NSLog(@"语音识别解析失败--%@", error);
}
}];
}
- (SFSpeechRecognitionTask *)recognitionTaskWithRequest1:(SFSpeechURLRecognitionRequest *)request{
return [self.speechRecognizer recognitionTaskWithRequest:request delegate:self];
}
- (void)didReceiveMemoryWarning {
[super didReceiveMemoryWarning];
}
#pragma mark- SFSpeechRecognitionTaskDelegate
- (void)speechRecognitionDidDetectSpeech:(SFSpeechRecognitionTask *)task
{
}
- (void)speechRecognitionTask:(SFSpeechRecognitionTask *)task didHypothesizeTranscription:(SFTranscription *)transcription {
}
- (void)speechRecognitionTask:(SFSpeechRecognitionTask *)task didFinishRecognition:(SFSpeechRecognitionResult *)recognitionResult {
NSDictionary *attributes = @{
NSFontAttributeName:[UIFont systemFontOfSize:18],
};
CGRect rect = [recognitionResult.bestTranscription.formattedString boundingRectWithSize:CGSizeMake(self.view.bounds.size.width - 100, CGFLOAT_MAX) options:NSStringDrawingUsesLineFragmentOrigin attributes:attributes context:nil];
self.recognizerLabel.text = recognitionResult.bestTranscription.formattedString;
self.recognizerLabel.frame = CGRectMake(50, 120, rect.size.width, rect.size.height);
}
- (void)speechRecognitionTaskFinishedReadingAudio:(SFSpeechRecognitionTask *)task {
}
- (void)speechRecognitionTaskWasCancelled:(SFSpeechRecognitionTask *)task {
}
- (void)speechRecognitionTask:(SFSpeechRecognitionTask *)task didFinishSuccessfully:(BOOL)successfully {
if (successfully) {
NSLog(@"全部解析完毕");
}
}
#pragma mark- getter
- (UILabel *)recognizerLabel {
if (!_recognizerLabel) {
_recognizerLabel = [[UILabel alloc] initWithFrame:CGRectMake(50, 120, self.view.bounds.size.width - 100, 100)];
_recognizerLabel.numberOfLines = 0;
_recognizerLabel.font = [UIFont preferredFontForTextStyle:UIFontTextStyleBody];
_recognizerLabel.adjustsFontForContentSizeCategory = YES;
_recognizerLabel.textColor = [UIColor orangeColor];
[self.view addSubview:_recognizerLabel];
}
return _recognizerLabel;
}
@end
4.第二种:识别即时语音录入
#import "ViewController.h"
#import
@interface ViewController ()
@property (nonatomic, strong) AVAudioEngine *audioEngine; // 声音处理器
@property (nonatomic, strong) SFSpeechRecognizer *speechRecognizer; // 语音识别器
@property (nonatomic, strong) SFSpeechAudioBufferRecognitionRequest *speechRequest; // 语音请求对象
@property (nonatomic, strong) SFSpeechRecognitionTask *currentSpeechTask; // 当前语音识别进程
@property (nonatomic, strong) UILabel *showLb; // 用于展现的label
@property (nonatomic, strong) UIButton *startBtn; // 启动按钮
@end
@implementation ViewController
- (void)viewDidLoad
{
[super viewDidLoad];
// 初始化
self.audioEngine = [AVAudioEngine new];
// 这里需要先设置一个AVAudioEngine和一个语音识别的请求对象SFSpeechAudioBufferRecognitionRequest
self.speechRecognizer = [SFSpeechRecognizer new];
self.startBtn.enabled = NO;
[SFSpeechRecognizer requestAuthorization:^(SFSpeechRecognizerAuthorizationStatus status)
{
if (status != SFSpeechRecognizerAuthorizationStatusAuthorized)
{
// 如果状态不是已授权则return
return;
}
// 初始化语音处理器的输入模式
[self.audioEngine.inputNode installTapOnBus:0 bufferSize:1024 format:[self.audioEngine.inputNode outputFormatForBus:0] block:^(AVAudioPCMBuffer * _Nonnull buffer,AVAudioTime * _Nonnull when)
{
// 为语音识别请求对象添加一个AudioPCMBuffer，来获取声音数据
[self.speechRequest appendAudioPCMBuffer:buffer];
}];
// 语音处理器准备就绪（会为一些audioEngine启动时所必须的资源开辟内存）
[self.audioEngine prepare];
self.startBtn.enabled = YES;
}];
}
- (void)onStartBtnClicked
{
if (self.currentSpeechTask.state == SFSpeechRecognitionTaskStateRunning)
{ // 如果当前进程状态是进行中
[self.startBtn setTitle:@"开始录制" forState:UIControlStateNormal];
// 停止语音识别
[self stopDictating];
}
else
{ // 进程状态不在进行中
[self.startBtn setTitle:@"停止录制" forState:UIControlStateNormal];
self.showLb.text = @"等待";
// 开启语音识别
[self startDictating];
}
}
- (void)startDictating
{
NSError *error;
// 启动声音处理器
[self.audioEngine startAndReturnError: &error];
// 初始化
self.speechRequest = [SFSpeechAudioBufferRecognitionRequest new];
// 使用speechRequest请求进行识别
self.currentSpeechTask =
[self.speechRecognizer recognitionTaskWithRequest:self.speechRequest resultHandler:^(SFSpeechRecognitionResult * _Nullable result,NSError * _Nullable error)
{
// 识别结果，识别后的操作
if (result == NULL) return;
self.showLb.text = result.bestTranscription.formattedString;
}];
}
- (void)stopDictating
{
// 停止声音处理器，停止语音识别请求进程
[self.audioEngine stop];
[self.speechRequest endAudio];
}
#pragma mark- getter
- (UILabel *)showLb {
if (!_showLb) {
_showLb = [[UILabel alloc] initWithFrame:CGRectMake(50, 180, self.view.bounds.size.width - 100, 100)];
_showLb.numberOfLines = 0;
_showLb.font = [UIFont preferredFontForTextStyle:UIFontTextStyleBody];
_showLb.text = @"等待中...";
_showLb.adjustsFontForContentSizeCategory = YES;
_showLb.textColor = [UIColor orangeColor];
[self.view addSubview:_showLb];
}
return _showLb;
}
- (UIButton *)startBtn {
if (!_startBtn) {
_startBtn = [UIButton buttonWithType:UIButtonTypeCustom];
_startBtn.frame = CGRectMake(50, 80, 80, 80);
[_startBtn addTarget:self action:@selector(onStartBtnClicked) forControlEvents:UIControlEventTouchUpInside];
[_startBtn setBackgroundColor:[UIColor redColor]];
[_startBtn setTitle:@"录音" forState:UIControlStateNormal];
[_startBtn setTitleColor:[UIColor whiteColor] forState:UIControlStateNormal];
[self.view addSubview:_startBtn];
}
return _startBtn;
}
@end
5.引申【各国语言代码】
6.知其然知其所以然
SpeechFramework框架中的重要类
SFSpeechRecognizer：这个类是语音识别的操作类，用于语音识别用户权限的申请，语言环境的设置，语音模式的设置以及向Apple服务发送语音识别的请求。
SFSpeechRecognitionTask：这个类是语音识别服务请求任务类，每一个语音识别请求都可以抽象为一个SFSpeechRecognitionTask实例，其中SFSpeechRecognitionTaskDelegate协议中约定了许多请求任务过程中的监听方法。
SFSpeechRecognitionRequest:语音识别请求类，需要通过其子类来进行实例化。
SFSpeechURLRecognitionRequest：通过音频URL来创建语音识别请求。
SFSpeechAudioBufferRecognitionRequest:通过音频流来创建语音识别请求。
SFSpeechRecognitionResult：语音识别请求结果类。
SFTranscription：语音转换后的信息类。
7.Demo地址
https://github.com/BeanMan/SpeechFramWork
参考文章:
http://www.jianshu.com/p/c4de4ee2134d
http://www.jianshu.com/p/487147605e08
站在巨人的肩膀上才有这些总结
菜鸟走向大牛，大家共同前进，如果觉得不错，请给个赞/关注。
一起交流学习，有问题随时欢迎联系，邮箱：[email protected]