diff --git a/README.md b/README.md index 3869b9d..6371df3 100644 --- a/README.md +++ b/README.md @@ -11,9 +11,34 @@ ​ 使用UE、C4D、DAZ、LIVE2D等三维引擎软件开发的数字形象可以与本“数字人控制器”对接，从而实现虚拟主播、数字导游、数字助手等。我们提供UE4对接的demo，但我们更鼓励用户自行实现喜欢的数字形象。 ​ 当然，若不考虑外观形象的话，本“数字人控制器”其实也可以独立使用的，可以充当一个语音助理。 -直播 -助理 -QA + +QA + +## 语音指令 + +- **关闭核心** + 关闭 + 再见 + 你走吧 +- **静音** + 静音 + 闭嘴 + 我想静静 +- **取消静音** + 取消静音 + 你在哪呢？ + 你可以说话了 +- **播放歌曲** + 播放歌曲 + 播放音乐 + 唱首歌 + 放首歌 + 听音乐 + 你会唱歌吗？ +- **暂停播放** + 暂停播放 + 别唱了 + 我不想听了 ## 环境 @@ -183,4 +208,5 @@ python main.py 技术交流群 -![mmqrcode1665648480395](C:\Users\Administrator\Documents\GitHub\Fay\images\mmqrcode1665648480395.png) \ No newline at end of file +直播 + diff --git a/ai_module/ms_tts_sdk.py b/ai_module/ms_tts_sdk.py index fade465..056876d 100644 --- a/ai_module/ms_tts_sdk.py +++ b/ai_module/ms_tts_sdk.py @@ -10,7 +10,7 @@ class Speech: def __init__(self): - self.__speech_config = speechsdk.SpeechConfig(subscription=cfg.key_ms_tts_key, region="eastasia") + self.__speech_config = speechsdk.SpeechConfig(subscription=cfg.key_ms_tts_key, region=cfg.key_ms_tts_region) self.__speech_config.speech_recognition_language = "zh-CN" self.__speech_config.speech_synthesis_voice_name = "zh-CN-XiaoxiaoNeural" self.__speech_config.set_speech_synthesis_output_format(speechsdk.SpeechSynthesisOutputFormat.Audio16Khz32KBitRateMonoMp3) diff --git a/config.json b/config.json index 39f3c37..b84d6e3 100644 --- a/config.json +++ b/config.json @@ -1,18 +1,18 @@ { "attribute": { - "age": "成年", - "birth": "中国", - "constellation": "水瓶座", - "contact": "微信123456789", - "gender": "男", - "hobby": "发呆", - "job": "产品布道者", - "name": "陈升", + "age": "\u6210\u5e74", + "birth": "\u4e2d\u56fd", + "constellation": "\u6c34\u74f6\u5ea7", + "contact": "qq467665317", + "gender": "\u7537", + "hobby": "\u53d1\u5446", + "job": "\u4ea7\u54c1\u5e03\u9053\u8005", + "name": "\u9648\u5347", "voice": "YUN_XI", - "zodiac": "蛇" + "zodiac": "\u86c7" }, "interact": { - "QnA": "E:/QnA/全局QnA.xlsx", + "QnA": "qa_demo.xlsx", "maxInteractTime": 15, "perception": { "chat": 7, @@ -21,11 +21,11 @@ "indifferent": 10, "join": 10 }, - "playSound": false + "playSound": true }, "items": [ { - "QnA": "E:/QnA/商品QnA.xlsx", + "QnA": "qa_demo.xlsx", "demoVideo": "C:/Demo.mp4", "enabled": false, "explain": { @@ -45,8 +45,8 @@ "url": "https://live.douyin.com/" }, "record": { - "device": "", - "enabled": false + "device": "\u9ea6\u514b\u98ce (HD Webcam C525)", + "enabled": true } } } \ No newline at end of file diff --git a/datas/data-20221013162403.csv b/datas/data-20221013162403.csv new file mode 100644 index 0000000..30ddb3f --- /dev/null +++ b/datas/data-20221013162403.csv @@ -0,0 +1,4 @@ +1665649464550,发言,,Hello hello hello hello hello + +1665649465854,主播,菲菲,我是你的好朋友 + diff --git a/datas/data-20221017112610.csv b/datas/data-20221017112610.csv new file mode 100644 index 0000000..738831f --- /dev/null +++ b/datas/data-20221017112610.csv @@ -0,0 +1,4 @@ +1665977183475,发言,,哈喽哈喽哈喽哈喽哈喽 + +1665977184516,主播,菲菲,我就理解为你在跟我打招呼好了 + diff --git a/datas/data-20221017112816.csv b/datas/data-20221017112816.csv new file mode 100644 index 0000000..5b400a9 --- /dev/null +++ b/datas/data-20221017112816.csv @@ -0,0 +1,12 @@ +1665977328657,发言,,今天天气怎么样 + +1665977329543,主播,菲菲,北京市今天全天晴，气温2℃ ~ 17℃，空气质量优，有北风6-7级，微冷，请注意保暖，预防感冒。 + +1665977356957,发言,,今天心情好吗 + +1665977357578,主播,菲菲,好你个鬼啊！ + +1665977433665,发言,,这个商品的优点是什么 + +1665977433825,主播,菲菲,没有优点！ + diff --git a/images/mmqrcode1665648480395.png b/images/4.png similarity index 100% rename from images/mmqrcode1665648480395.png rename to images/4.png diff --git a/images/5.png b/images/5.png new file mode 100644 index 0000000..79759c7 Binary files /dev/null and b/images/5.png differ diff --git a/qa_demo.xlsx b/qa_demo.xlsx new file mode 100644 index 0000000..ee3aaf3 Binary files /dev/null and b/qa_demo.xlsx differ diff --git a/requirements.txt b/requirements.txt index af3cb72..210673d 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,6 +1,6 @@ requests~=2.26.0 selenium~=4.1.3 -numpy~=1.19.5 +numpy~=1.22.0 pyaudio~=0.2.11 websockets~=10.2 ws4py~=0.5.1 diff --git a/samples/sample-1665977330241.mp3 b/samples/sample-1665977330241.mp3 new file mode 100644 index 0000000..be5333c Binary files /dev/null and b/samples/sample-1665977330241.mp3 differ diff --git a/samples/sample-1665977357951.mp3 b/samples/sample-1665977357951.mp3 new file mode 100644 index 0000000..54c1975 Binary files /dev/null and b/samples/sample-1665977357951.mp3 differ diff --git a/samples/sample-1665977434134.mp3 b/samples/sample-1665977434134.mp3 new file mode 100644 index 0000000..374c0c0 Binary files /dev/null and b/samples/sample-1665977434134.mp3 differ diff --git a/system.conf b/system.conf index 2b9927b..dd9a62b 100644 --- a/system.conf +++ b/system.conf @@ -10,11 +10,15 @@ ali_nls_app_key= # 微软 文字转语音 服务密钥 ms_tts_key= +ms_tts_region= # 讯飞 自然语言处理 服务密钥 xf_aiui_app_id= xf_aiui_api_key= +# xf_aiui_app_id=aa00cfa0 +# xf_aiui_api_key=9a22da6450e950541c39d09ec29b1786 + # 讯飞 情绪分析 服务密钥 xf_ltp_app_id= xf_ltp_api_key= diff --git a/utils/config_util.py b/utils/config_util.py index ad717f9..f059c3e 100644 --- a/utils/config_util.py +++ b/utils/config_util.py @@ -10,6 +10,7 @@ key_ali_nls_key_secret = None key_ali_nls_app_key = None key_ms_tts_key = None +Key_ms_tts_region = None key_xf_aiui_app_id = None key_xf_aiui_api_key = None key_xf_ltp_app_id = None @@ -23,6 +24,7 @@ def load_config(): global key_ali_nls_key_secret global key_ali_nls_app_key global key_ms_tts_key + global key_ms_tts_region global key_xf_aiui_app_id global key_xf_aiui_api_key global key_xf_ltp_app_id @@ -35,6 +37,7 @@ def load_config(): key_ali_nls_key_secret = system_config.get('key', 'ali_nls_key_secret') key_ali_nls_app_key = system_config.get('key', 'ali_nls_app_key') key_ms_tts_key = system_config.get('key', 'ms_tts_key') + key_ms_tts_region = system_config.get('key', 'ms_tts_region') key_xf_aiui_app_id = system_config.get('key', 'xf_aiui_app_id') key_xf_aiui_api_key = system_config.get('key', 'xf_aiui_api_key') key_xf_ltp_app_id = system_config.get('key', 'xf_ltp_app_id')