You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

246 lines
6.7 KiB

import 'dart:async';
import 'dart:typed_data';
import 'package:get/get.dart';
import '../../../core/utils/logger.dart';
import '../../../data/services/asr_service.dart';
import '../../../data/services/speech_impl/xunfei_asr_service.dart';
import '../../../data/services/tts_service.dart';
import '../../../data/services/language_manager.dart';
import '../../../data/services/volcano_translation_service.dart';
class FTFTranslationController extends GetxController
with GetSingleTickerProviderStateMixin {
final messages = <FTFTranslationMessage>[].obs;
final isChineseInput = true.obs;
final leftLanguage = '中文'.obs;
final rightLanguage = 'English'.obs;
final isLeftInput = true.obs;
final supportedLanguages = const [
'中文',
'English',
'日本語',
'한국어',
'Español',
];
late final AsrService _asrService;
StreamSubscription? _recognitionSubscription;
RxString intermediateContent = ''.obs;
RxString finalContent = ''.obs;
BytesBuilder _originaBytes = BytesBuilder(); //原始音频
final VolcanoTranslationService _translationService =
Get.find<VolcanoTranslationService>();
final LanguageManager _languageManager = Get.find<LanguageManager>();
// 当前使用的TTS服务
late TtsService _ttsService;
final isTranslating = false.obs;
final sourceLanguageCode = 'zh-CN'.obs;
final targetLanguageCode = 'en-US'.obs;
final isTtsEnabled = true.obs;
@override
void onInit() {
super.onInit();
Get.put(XunfeiAsrService());
final TtsService _ttsService = Get.find<TtsService>();
_asrService = Get.find<XunfeiAsrService>();
_InfoRecorder();
}
@override
void onClose() {
_asrService.dispose();
_recognitionSubscription?.cancel();
super.onClose();
}
//开始录音
Future<void> _InfoRecorder() async {
final recognitionStream = await _asrService.recognizeCallback();
_recognitionSubscription = recognitionStream.listen(
_handleRecognitionEvent,
);
}
//开始录音
Future<void> _startRecorder() async {
await _asrService.startContinuousRecognition(false);
}
//结束录音
Future<void> _stopRecorder() async {
await _asrService.stopContinuousRecognition();
}
// 处理语音识别事件
void _handleRecognitionEvent(RecognitionEvent event) {
switch (event.type) {
case RecognitionEventType.intermediateResult:
intermediateContent.value = event.text;
handleFinalResult(event.text);
break;
case RecognitionEventType.finalResult:
finalContent.value += _spliceText(event);
intermediateContent.value = '';
_originaBytes.add(event.audio!);
handleIntermediateResult(event.text);
break;
default:
// 不做任何处理
break;
}
}
// 翻译文本
Future<String?> translateText(String sourceText,
{bool isFinal = false}) async {
if (sourceText.isEmpty) return null;
isTranslating.value = true;
String? translationResult;
try {
// 根据检测到的语言确定源语言和目标语言
final bool shouldSwap =
intermediateContent.value == sourceLanguageCode.value;
final detectedSourceLanguageCode =
shouldSwap ? sourceLanguageCode.value : targetLanguageCode.value;
final detectedTargetLanguageCode =
shouldSwap ? targetLanguageCode.value : sourceLanguageCode.value;
// 调用翻译服务
translationResult = await _translationService.translateText(
text: sourceText,
sourceLanguageCode: detectedSourceLanguageCode,
targetLanguageCode: detectedTargetLanguageCode,
);
if (translationResult != null) {
// 查找匹配的项目 - 优先使用timestamp查找
int index = -1;
// 播放TTS - 只在最终结果时播放
if (isTtsEnabled.value && isFinal) {
// Logger.info('播放翻译文本: ${translationResult}');
await playTranslatedText(translationResult);
}
}
} catch (e) {
Logger.error('翻译失败: ${e.toString()}');
} finally {
isTranslating.value = false;
}
return translationResult;
}
// 处理中间识别结果
void handleIntermediateResult(String text) {
if (text.isEmpty) return;
translateText(text, isFinal: false);
}
// 处理最终识别结果
Future<void> handleFinalResult(String text) async {
if (text.isEmpty) return;
// 使用项目的时间戳进行翻译
translateText(text, isFinal: true);
}
// 播放翻译文本
Future<void> playTranslatedText(String text) async {
if (text.isEmpty) return;
try {
final bool shouldSwap =
intermediateContent.value == targetLanguageCode.value;
final detectedTargetLanguageCode =
shouldSwap ? sourceLanguageCode.value : targetLanguageCode.value;
final voiceName = _languageManager
.getTtsVoiceNameByAsrCode(detectedTargetLanguageCode) ??
'en-US-AriaNeural';
await _ttsService.setVoice(voiceName);
await _ttsService.speakOnce(text);
} catch (e) {
Logger.error('播放翻译失败: ${e.toString()}');
}
}
String _spliceText(RecognitionEvent event) {
String eventText = event.text;
String text = '';
if (finalContent.value.isNotEmpty) {
if (event.role != '') {
final punctuations = {
',',
'。',
'!',
'?',
';',
':',
',',
'.',
':',
';',
'!',
'?'
};
final firstChar = eventText[0];
if (punctuations.contains(firstChar)) {
text += '$firstChar\n';
eventText = eventText.substring(1);
} else {
text += '\n';
}
text += '说话人${event.role}:';
}
} else {
text += '说话人${event.role}:';
}
text += eventText;
return text;
}
void addMessage(String text) {
final fromLang =
isLeftInput.value ? leftLanguage.value : rightLanguage.value;
final toLang = isLeftInput.value ? rightLanguage.value : leftLanguage.value;
messages.add(
FTFTranslationMessage(
original: text,
translated: '[$fromLang → $toLang] $text (翻译模拟)',
isChineseSpeaker: isLeftInput.value,
),
);
}
void swapLanguages() {
final temp = leftLanguage.value;
leftLanguage.value = rightLanguage.value;
rightLanguage.value = temp;
isLeftInput.value = !isLeftInput.value;
}
void toggleInputSide(bool isLeft) => isLeftInput.value = isLeft;
}
class FTFTranslationMessage {
final String original;
final String translated;
final bool isChineseSpeaker;
FTFTranslationMessage({
required this.original,
required this.translated,
required this.isChineseSpeaker,
});
}