1. 研究背景

在很多公司中要求不能调用云端的API,特别是政府单位和金融公司,在通话录音和会议录音等高保密级音频数据一般是不能走网络的,也就是我们必须要在公司内部机房中部署一套自己的ASR接口给公司的项目去调用。
在众多的开源ASR中,这个Whisper和FunASR是star数量很高的开源项目,其中这个whisper适合多语种情况,支持99种国际常用的语言,国内支持粤语和普通话,但是对于普通话的识别准确率不如FunASR中的Paraformer模型,所以这里基于FunASR来编写开发的API接口。并且FunASR官方中提供的是docker版本的,方便你的部署,不过这个docker版本的不支持区分说话人,下面自己使用python基于funasr这个依赖库开发了API接口,用于区分说话人并且进行语音识别。

2. 支持哪些系统部署

可以在任何支持运行python的系统中部署,目前已经验证了可以在Ubuntu,CentOS7,RedHat7,openEuler 22.03 (LTS-SP4)中部署,都是x86指令集的CPU,其它系统还没尝试过,大家也可以自己尝试一下。

3. 可以在没有网服务器中部署吗

可以的,不过部署难度会比有网的大,在2023年的时候给深圳一家银行内部部署过,确实挺麻烦的,银行服务的系统是隔离了外部网络的,内网部署会比较费时间,但是可以部署的,因为我之前部署过,在2023年的时候。

4. 这个接口可以返回字级别的时间戳吗

对于通话录音转写来说,不需要字级别的时间戳,但是对于有些场景有些公司需要用到字级别的时间戳,模型刚好也支持字级别时间戳输出,我之前开发的接口,忽略了字级别时间戳,因为用不上,最近有公司找到我让我添加字级别的时间戳,昨天开发完成了,效果如下截图所示。
在这里插入图片描述
具体返回的json数据我也给你粘贴出来,你们看看是不是符合你们的需求。

{
    "code": 200,
    "status": "success",
    "message": "转写完成",
    "data": {
        "text": "我是第一个说话人,现在我录制一段声音来测试一下,直接跑路了。我我连传达的机会都没有,我现在回到我车上,我想了一下,我明天他二十四小时失恋才能报警吗?我明天下午的时候我就去报警,但是我很庆幸的是,我今天三十号来店里面了,如果我今天不来,他房租到期了之后,东西都搬空了,那个时候来也没有意义了。幸好这个是第二个人的一个声音,然后这段音频中包含了两个人的声音,一个是我自己的一个声音。然后另外一个是我播放啊,另外一个呃视频里面的一个声音。然后现在我们啊来试一下啊,现在有一分钟的一个音频了,我们试一下吧。",
        "sentences": [
            {
                "text": "我是第一个说话人,",
                "start": "00:00:01.420",
                "end": "00:00:03.480",
                "spk": 0,
                "word_info": [
                    {
                        "word": "我",
                        "start": "00:00:01.420",
                        "end": "00:00:01.660"
                    },
                    {
                        "word": "是",
                        "start": "00:00:01.700",
                        "end": "00:00:01.940"
                    },
                    {
                        "word": "第",
                        "start": "00:00:02.100",
                        "end": "00:00:02.300"
                    },
                    {
                        "word": "一",
                        "start": "00:00:02.300",
                        "end": "00:00:02.480"
                    },
                    {
                        "word": "个",
                        "start": "00:00:02.480",
                        "end": "00:00:02.720"
                    },
                    {
                        "word": "说",
                        "start": "00:00:02.820",
                        "end": "00:00:03.000"
                    },
                    {
                        "word": "话",
                        "start": "00:00:03.000",
                        "end": "00:00:03.240"
                    },
                    {
                        "word": "人",
                        "start": "00:00:03.240",
                        "end": "00:00:03.480"
                    }
                ]
            },
            {
                "text": "现在我录制一段声音来测试一下,",
                "start": "00:00:03.680",
                "end": "00:00:07.335",
                "spk": 0,
                "word_info": [
                    {
                        "word": "现",
                        "start": "00:00:03.680",
                        "end": "00:00:03.900"
                    },
                    {
                        "word": "在",
                        "start": "00:00:03.900",
                        "end": "00:00:04.140"
                    },
                    {
                        "word": "我",
                        "start": "00:00:04.220",
                        "end": "00:00:04.460"
                    },
                    {
                        "word": "录",
                        "start": "00:00:04.540",
                        "end": "00:00:04.780"
                    },
                    {
                        "word": "制",
                        "start": "00:00:04.780",
                        "end": "00:00:05.000"
                    },
                    {
                        "word": "一",
                        "start": "00:00:05.000",
                        "end": "00:00:05.140"
                    },
                    {
                        "word": "段",
                        "start": "00:00:05.140",
                        "end": "00:00:05.380"
                    },
                    {
                        "word": "声",
                        "start": "00:00:05.480",
                        "end": "00:00:05.680"
                    },
                    {
                        "word": "音",
                        "start": "00:00:05.680",
                        "end": "00:00:05.900"
                    },
                    {
                        "word": "来",
                        "start": "00:00:05.900",
                        "end": "00:00:06.140"
                    },
                    {
                        "word": "测",
                        "start": "00:00:06.240",
                        "end": "00:00:06.480"
                    },
                    {
                        "word": "试",
                        "start": "00:00:06.500",
                        "end": "00:00:06.720"
                    },
                    {
                        "word": "一",
                        "start": "00:00:06.720",
                        "end": "00:00:06.920"
                    },
                    {
                        "word": "下",
                        "start": "00:00:06.920",
                        "end": "00:00:07.335"
                    }
                ]
            },
            {
                "text": "直接跑路了。",
                "start": "00:00:09.360",
                "end": "00:00:10.160",
                "spk": 1,
                "word_info": [
                    {
                        "word": "直",
                        "start": "00:00:09.360",
                        "end": "00:00:09.520"
                    },
                    {
                        "word": "接",
                        "start": "00:00:09.520",
                        "end": "00:00:09.660"
                    },
                    {
                        "word": "跑",
                        "start": "00:00:09.660",
                        "end": "00:00:09.880"
                    },
                    {
                        "word": "路",
                        "start": "00:00:09.880",
                        "end": "00:00:10.040"
                    },
                    {
                        "word": "了",
                        "start": "00:00:10.040",
                        "end": "00:00:10.160"
                    }
                ]
            },
            {
                "text": "我我连传达的机会都没有,",
                "start": "00:00:10.160",
                "end": "00:00:13.175",
                "spk": 1,
                "word_info": [
                    {
                        "word": "我",
                        "start": "00:00:10.160",
                        "end": "00:00:10.400"
                    },
                    {
                        "word": "我",
                        "start": "00:00:10.540",
                        "end": "00:00:10.660"
                    },
                    {
                        "word": "连",
                        "start": "00:00:10.660",
                        "end": "00:00:10.900"
                    },
                    {
                        "word": "传",
                        "start": "00:00:11.100",
                        "end": "00:00:11.340"
                    },
                    {
                        "word": "达",
                        "start": "00:00:11.340",
                        "end": "00:00:11.580"
                    },
                    {
                        "word": "的",
                        "start": "00:00:11.580",
                        "end": "00:00:11.820"
                    },
                    {
                        "word": "机",
                        "start": "00:00:12.120",
                        "end": "00:00:12.280"
                    },
                    {
                        "word": "会",
                        "start": "00:00:12.280",
                        "end": "00:00:12.520"
                    },
                    {
                        "word": "都",
                        "start": "00:00:12.520",
                        "end": "00:00:12.700"
                    },
                    {
                        "word": "没",
                        "start": "00:00:12.700",
                        "end": "00:00:12.880"
                    },
                    {
                        "word": "有",
                        "start": "00:00:12.880",
                        "end": "00:00:13.175"
                    }
                ]
            },
            {
                "text": "我现在回到我车上,",
                "start": "00:00:16.110",
                "end": "00:00:17.730",
                "spk": 1,
                "word_info": [
                    {
                        "word": "我",
                        "start": "00:00:16.110",
                        "end": "00:00:16.270"
                    },
                    {
                        "word": "现",
                        "start": "00:00:16.270",
                        "end": "00:00:16.430"
                    },
                    {
                        "word": "在",
                        "start": "00:00:16.430",
                        "end": "00:00:16.670"
                    },
                    {
                        "word": "回",
                        "start": "00:00:16.810",
                        "end": "00:00:17.010"
                    },
                    {
                        "word": "到",
                        "start": "00:00:17.010",
                        "end": "00:00:17.170"
                    },
                    {
                        "word": "我",
                        "start": "00:00:17.170",
                        "end": "00:00:17.370"
                    },
                    {
                        "word": "车",
                        "start": "00:00:17.370",
                        "end": "00:00:17.490"
                    },
                    {
                        "word": "上",
                        "start": "00:00:17.490",
                        "end": "00:00:17.730"
                    }
                ]
            },
            {
                "text": "我想了一下,",
                "start": "00:00:18.530",
                "end": "00:00:19.410",
                "spk": 1,
                "word_info": [
                    {
                        "word": "我",
                        "start": "00:00:18.530",
                        "end": "00:00:18.750"
                    },
                    {
                        "word": "想",
                        "start": "00:00:18.750",
                        "end": "00:00:18.970"
                    },
                    {
                        "word": "了",
                        "start": "00:00:18.970",
                        "end": "00:00:19.090"
                    },
                    {
                        "word": "一",
                        "start": "00:00:19.090",
                        "end": "00:00:19.170"
                    },
                    {
                        "word": "下",
                        "start": "00:00:19.170",
                        "end": "00:00:19.410"
                    }
                ]
            },
            {
                "text": "我明天他二十四小时失恋才能报警吗?",
                "start": "00:00:19.850",
                "end": "00:00:23.490",
                "spk": 1,
                "word_info": [
                    {
                        "word": "我",
                        "start": "00:00:19.850",
                        "end": "00:00:20.070"
                    },
                    {
                        "word": "明",
                        "start": "00:00:20.070",
                        "end": "00:00:20.270"
                    },
                    {
                        "word": "天",
                        "start": "00:00:20.270",
                        "end": "00:00:20.775"
                    },
                    {
                        "word": "他",
                        "start": "00:00:21.570",
                        "end": "00:00:21.750"
                    },
                    {
                        "word": "二",
                        "start": "00:00:21.750",
                        "end": "00:00:21.850"
                    },
                    {
                        "word": "十",
                        "start": "00:00:21.850",
                        "end": "00:00:21.970"
                    },
                    {
                        "word": "四",
                        "start": "00:00:21.970",
                        "end": "00:00:22.110"
                    },
                    {
                        "word": "小",
                        "start": "00:00:22.110",
                        "end": "00:00:22.250"
                    },
                    {
                        "word": "时",
                        "start": "00:00:22.250",
                        "end": "00:00:22.390"
                    },
                    {
                        "word": "失",
                        "start": "00:00:22.390",
                        "end": "00:00:22.490"
                    },
                    {
                        "word": "恋",
                        "start": "00:00:22.490",
                        "end": "00:00:22.630"
                    },
                    {
                        "word": "才",
                        "start": "00:00:22.630",
                        "end": "00:00:22.710"
                    },
                    {
                        "word": "能",
                        "start": "00:00:22.710",
                        "end": "00:00:22.910"
                    },
                    {
                        "word": "报",
                        "start": "00:00:22.910",
                        "end": "00:00:23.070"
                    },
                    {
                        "word": "警",
                        "start": "00:00:23.070",
                        "end": "00:00:23.250"
                    },
                    {
                        "word": "吗",
                        "start": "00:00:23.250",
                        "end": "00:00:23.490"
                    }
                ]
            },
            {
                "text": "我明天下午的时候我就去报警,",
                "start": "00:00:23.850",
                "end": "00:00:27.420",
                "spk": 1,
                "word_info": [
                    {
                        "word": "我",
                        "start": "00:00:23.850",
                        "end": "00:00:24.030"
                    },
                    {
                        "word": "明",
                        "start": "00:00:24.030",
                        "end": "00:00:24.190"
                    },
                    {
                        "word": "天",
                        "start": "00:00:24.190",
                        "end": "00:00:24.430"
                    },
                    {
                        "word": "下",
                        "start": "00:00:24.430",
                        "end": "00:00:24.670"
                    },
                    {
                        "word": "午",
                        "start": "00:00:24.670",
                        "end": "00:00:25.025"
                    },
                    {
                        "word": "的",
                        "start": "00:00:26.020",
                        "end": "00:00:26.200"
                    },
                    {
                        "word": "时",
                        "start": "00:00:26.200",
                        "end": "00:00:26.420"
                    },
                    {
                        "word": "候",
                        "start": "00:00:26.420",
                        "end": "00:00:26.600"
                    },
                    {
                        "word": "我",
                        "start": "00:00:26.600",
                        "end": "00:00:26.720"
                    },
                    {
                        "word": "就",
                        "start": "00:00:26.720",
                        "end": "00:00:26.820"
                    },
                    {
                        "word": "去",
                        "start": "00:00:26.820",
                        "end": "00:00:27.020"
                    },
                    {
                        "word": "报",
                        "start": "00:00:27.020",
                        "end": "00:00:27.180"
                    },
                    {
                        "word": "警",
                        "start": "00:00:27.180",
                        "end": "00:00:27.420"
                    }
                ]
            },
            {
                "text": "但是我很庆幸的是,",
                "start": "00:00:28.080",
                "end": "00:00:29.660",
                "spk": 1,
                "word_info": [
                    {
                        "word": "但",
                        "start": "00:00:28.080",
                        "end": "00:00:28.240"
                    },
                    {
                        "word": "是",
                        "start": "00:00:28.240",
                        "end": "00:00:28.380"
                    },
                    {
                        "word": "我",
                        "start": "00:00:28.380",
                        "end": "00:00:28.540"
                    },
                    {
                        "word": "很",
                        "start": "00:00:28.540",
                        "end": "00:00:28.780"
                    },
                    {
                        "word": "庆",
                        "start": "00:00:28.820",
                        "end": "00:00:29.060"
                    },
                    {
                        "word": "幸",
                        "start": "00:00:29.060",
                        "end": "00:00:29.300"
                    },
                    {
                        "word": "的",
                        "start": "00:00:29.300",
                        "end": "00:00:29.420"
                    },
                    {
                        "word": "是",
                        "start": "00:00:29.420",
                        "end": "00:00:29.660"
                    }
                ]
            },
            {
                "text": "我今天三十号来店里面了,",
                "start": "00:00:29.660",
                "end": "00:00:33.700",
                "spk": 1,
                "word_info": [
                    {
                        "word": "我",
                        "start": "00:00:29.660",
                        "end": "00:00:30.015"
                    },
                    {
                        "word": "今",
                        "start": "00:00:30.970",
                        "end": "00:00:31.150"
                    },
                    {
                        "word": "天",
                        "start": "00:00:31.150",
                        "end": "00:00:31.390"
                    },
                    {
                        "word": "三",
                        "start": "00:00:31.410",
                        "end": "00:00:31.550"
                    },
                    {
                        "word": "十",
                        "start": "00:00:31.550",
                        "end": "00:00:31.710"
                    },
                    {
                        "word": "号",
                        "start": "00:00:31.710",
                        "end": "00:00:32.065"
                    },
                    {
                        "word": "来",
                        "start": "00:00:32.900",
                        "end": "00:00:33.080"
                    },
                    {
                        "word": "店",
                        "start": "00:00:33.080",
                        "end": "00:00:33.280"
                    },
                    {
                        "word": "里",
                        "start": "00:00:33.280",
                        "end": "00:00:33.440"
                    },
                    {
                        "word": "面",
                        "start": "00:00:33.440",
                        "end": "00:00:33.560"
                    },
                    {
                        "word": "了",
                        "start": "00:00:33.560",
                        "end": "00:00:33.700"
                    }
                ]
            },
            {
                "text": "如果我今天不来,",
                "start": "00:00:33.700",
                "end": "00:00:34.800",
                "spk": 1,
                "word_info": [
                    {
                        "word": "如",
                        "start": "00:00:33.700",
                        "end": "00:00:33.800"
                    },
                    {
                        "word": "果",
                        "start": "00:00:33.800",
                        "end": "00:00:33.980"
                    },
                    {
                        "word": "我",
                        "start": "00:00:33.980",
                        "end": "00:00:34.120"
                    },
                    {
                        "word": "今",
                        "start": "00:00:34.120",
                        "end": "00:00:34.220"
                    },
                    {
                        "word": "天",
                        "start": "00:00:34.220",
                        "end": "00:00:34.400"
                    },
                    {
                        "word": "不",
                        "start": "00:00:34.400",
                        "end": "00:00:34.560"
                    },
                    {
                        "word": "来",
                        "start": "00:00:34.560",
                        "end": "00:00:34.800"
                    }
                ]
            },
            {
                "text": "他房租到期了之后,",
                "start": "00:00:34.820",
                "end": "00:00:36.420",
                "spk": 1,
                "word_info": [
                    {
                        "word": "他",
                        "start": "00:00:34.820",
                        "end": "00:00:35.000"
                    },
                    {
                        "word": "房",
                        "start": "00:00:35.000",
                        "end": "00:00:35.160"
                    },
                    {
                        "word": "租",
                        "start": "00:00:35.160",
                        "end": "00:00:35.400"
                    },
                    {
                        "word": "到",
                        "start": "00:00:35.420",
                        "end": "00:00:35.640"
                    },
                    {
                        "word": "期",
                        "start": "00:00:35.640",
                        "end": "00:00:35.820"
                    },
                    {
                        "word": "了",
                        "start": "00:00:35.820",
                        "end": "00:00:36.020"
                    },
                    {
                        "word": "之",
                        "start": "00:00:36.020",
                        "end": "00:00:36.180"
                    },
                    {
                        "word": "后",
                        "start": "00:00:36.180",
                        "end": "00:00:36.420"
                    }
                ]
            },
            {
                "text": "东西都搬空了,",
                "start": "00:00:36.740",
                "end": "00:00:37.840",
                "spk": 1,
                "word_info": [
                    {
                        "word": "东",
                        "start": "00:00:36.740",
                        "end": "00:00:36.940"
                    },
                    {
                        "word": "西",
                        "start": "00:00:36.940",
                        "end": "00:00:37.060"
                    },
                    {
                        "word": "都",
                        "start": "00:00:37.060",
                        "end": "00:00:37.260"
                    },
                    {
                        "word": "搬",
                        "start": "00:00:37.260",
                        "end": "00:00:37.480"
                    },
                    {
                        "word": "空",
                        "start": "00:00:37.480",
                        "end": "00:00:37.660"
                    },
                    {
                        "word": "了",
                        "start": "00:00:37.660",
                        "end": "00:00:37.840"
                    }
                ]
            },
            {
                "text": "那个时候来也没有意义了。",
                "start": "00:00:37.840",
                "end": "00:00:39.260",
                "spk": 1,
                "word_info": [
                    {
                        "word": "那",
                        "start": "00:00:37.840",
                        "end": "00:00:37.920"
                    },
                    {
                        "word": "个",
                        "start": "00:00:37.920",
                        "end": "00:00:38.020"
                    },
                    {
                        "word": "时",
                        "start": "00:00:38.020",
                        "end": "00:00:38.120"
                    },
                    {
                        "word": "候",
                        "start": "00:00:38.120",
                        "end": "00:00:38.260"
                    },
                    {
                        "word": "来",
                        "start": "00:00:38.260",
                        "end": "00:00:38.420"
                    },
                    {
                        "word": "也",
                        "start": "00:00:38.420",
                        "end": "00:00:38.540"
                    },
                    {
                        "word": "没",
                        "start": "00:00:38.540",
                        "end": "00:00:38.660"
                    },
                    {
                        "word": "有",
                        "start": "00:00:38.660",
                        "end": "00:00:38.780"
                    },
                    {
                        "word": "意",
                        "start": "00:00:38.780",
                        "end": "00:00:38.900"
                    },
                    {
                        "word": "义",
                        "start": "00:00:38.900",
                        "end": "00:00:39.020"
                    },
                    {
                        "word": "了",
                        "start": "00:00:39.020",
                        "end": "00:00:39.260"
                    }
                ]
            },
            {
                "text": "幸好这个是第二个人的一个声音,",
                "start": "00:00:39.440",
                "end": "00:00:44.550",
                "spk": 0,
                "word_info": [
                    {
                        "word": "幸",
                        "start": "00:00:39.440",
                        "end": "00:00:39.620"
                    },
                    {
                        "word": "好",
                        "start": "00:00:39.620",
                        "end": "00:00:40.035"
                    },
                    {
                        "word": "这",
                        "start": "00:00:41.550",
                        "end": "00:00:41.750"
                    },
                    {
                        "word": "个",
                        "start": "00:00:41.750",
                        "end": "00:00:41.930"
                    },
                    {
                        "word": "是",
                        "start": "00:00:41.930",
                        "end": "00:00:42.170"
                    },
                    {
                        "word": "第",
                        "start": "00:00:42.450",
                        "end": "00:00:42.630"
                    },
                    {
                        "word": "二",
                        "start": "00:00:42.630",
                        "end": "00:00:42.810"
                    },
                    {
                        "word": "个",
                        "start": "00:00:42.810",
                        "end": "00:00:42.930"
                    },
                    {
                        "word": "人",
                        "start": "00:00:42.930",
                        "end": "00:00:43.170"
                    },
                    {
                        "word": "的",
                        "start": "00:00:43.230",
                        "end": "00:00:43.470"
                    },
                    {
                        "word": "一",
                        "start": "00:00:43.510",
                        "end": "00:00:43.650"
                    },
                    {
                        "word": "个",
                        "start": "00:00:43.650",
                        "end": "00:00:43.890"
                    },
                    {
                        "word": "声",
                        "start": "00:00:44.050",
                        "end": "00:00:44.290"
                    },
                    {
                        "word": "音",
                        "start": "00:00:44.310",
                        "end": "00:00:44.550"
                    }
                ]
            },
            {
                "text": "然后这段音频中包含了两个人的声音,",
                "start": "00:00:44.850",
                "end": "00:00:48.010",
                "spk": 0,
                "word_info": [
                    {
                        "word": "然",
                        "start": "00:00:44.850",
                        "end": "00:00:45.030"
                    },
                    {
                        "word": "后",
                        "start": "00:00:45.030",
                        "end": "00:00:45.270"
                    },
                    {
                        "word": "这",
                        "start": "00:00:45.350",
                        "end": "00:00:45.510"
                    },
                    {
                        "word": "段",
                        "start": "00:00:45.510",
                        "end": "00:00:45.710"
                    },
                    {
                        "word": "音",
                        "start": "00:00:45.710",
                        "end": "00:00:45.870"
                    },
                    {
                        "word": "频",
                        "start": "00:00:45.870",
                        "end": "00:00:46.110"
                    },
                    {
                        "word": "中",
                        "start": "00:00:46.110",
                        "end": "00:00:46.350"
                    },
                    {
                        "word": "包",
                        "start": "00:00:46.510",
                        "end": "00:00:46.710"
                    },
                    {
                        "word": "含",
                        "start": "00:00:46.710",
                        "end": "00:00:46.950"
                    },
                    {
                        "word": "了",
                        "start": "00:00:46.950",
                        "end": "00:00:47.110"
                    },
                    {
                        "word": "两",
                        "start": "00:00:47.110",
                        "end": "00:00:47.310"
                    },
                    {
                        "word": "个",
                        "start": "00:00:47.310",
                        "end": "00:00:47.490"
                    },
                    {
                        "word": "人",
                        "start": "00:00:47.490",
                        "end": "00:00:47.570"
                    },
                    {
                        "word": "的",
                        "start": "00:00:47.570",
                        "end": "00:00:47.670"
                    },
                    {
                        "word": "声",
                        "start": "00:00:47.670",
                        "end": "00:00:47.770"
                    },
                    {
                        "word": "音",
                        "start": "00:00:47.770",
                        "end": "00:00:48.010"
                    }
                ]
            },
            {
                "text": "一个是我自己的一个声音。",
                "start": "00:00:48.030",
                "end": "00:00:49.870",
                "spk": 0,
                "word_info": [
                    {
                        "word": "一",
                        "start": "00:00:48.030",
                        "end": "00:00:48.130"
                    },
                    {
                        "word": "个",
                        "start": "00:00:48.130",
                        "end": "00:00:48.310"
                    },
                    {
                        "word": "是",
                        "start": "00:00:48.310",
                        "end": "00:00:48.550"
                    },
                    {
                        "word": "我",
                        "start": "00:00:48.570",
                        "end": "00:00:48.810"
                    },
                    {
                        "word": "自",
                        "start": "00:00:48.810",
                        "end": "00:00:48.910"
                    },
                    {
                        "word": "己",
                        "start": "00:00:48.910",
                        "end": "00:00:49.090"
                    },
                    {
                        "word": "的",
                        "start": "00:00:49.090",
                        "end": "00:00:49.230"
                    },
                    {
                        "word": "一",
                        "start": "00:00:49.230",
                        "end": "00:00:49.329"
                    },
                    {
                        "word": "个",
                        "start": "00:00:49.329",
                        "end": "00:00:49.430"
                    },
                    {
                        "word": "声",
                        "start": "00:00:49.430",
                        "end": "00:00:49.630"
                    },
                    {
                        "word": "音",
                        "start": "00:00:49.630",
                        "end": "00:00:49.870"
                    }
                ]
            },
            {
                "text": "然后另外一个是我播放啊,",
                "start": "00:00:50.050",
                "end": "00:00:52.430",
                "spk": 0,
                "word_info": [
                    {
                        "word": "然",
                        "start": "00:00:50.050",
                        "end": "00:00:50.230"
                    },
                    {
                        "word": "后",
                        "start": "00:00:50.230",
                        "end": "00:00:50.370"
                    },
                    {
                        "word": "另",
                        "start": "00:00:50.370",
                        "end": "00:00:50.470"
                    },
                    {
                        "word": "外",
                        "start": "00:00:50.470",
                        "end": "00:00:50.670"
                    },
                    {
                        "word": "一",
                        "start": "00:00:50.670",
                        "end": "00:00:50.770"
                    },
                    {
                        "word": "个",
                        "start": "00:00:50.770",
                        "end": "00:00:50.950"
                    },
                    {
                        "word": "是",
                        "start": "00:00:50.950",
                        "end": "00:00:51.130"
                    },
                    {
                        "word": "我",
                        "start": "00:00:51.130",
                        "end": "00:00:51.350"
                    },
                    {
                        "word": "播",
                        "start": "00:00:51.350",
                        "end": "00:00:51.530"
                    },
                    {
                        "word": "放",
                        "start": "00:00:51.530",
                        "end": "00:00:51.770"
                    },
                    {
                        "word": "啊",
                        "start": "00:00:52.190",
                        "end": "00:00:52.430"
                    }
                ]
            },
            {
                "text": "另外一个呃视频里面的一个声音。",
                "start": "00:00:52.470",
                "end": "00:00:55.250",
                "spk": 0,
                "word_info": [
                    {
                        "word": "另",
                        "start": "00:00:52.470",
                        "end": "00:00:52.670"
                    },
                    {
                        "word": "外",
                        "start": "00:00:52.670",
                        "end": "00:00:52.870"
                    },
                    {
                        "word": "一",
                        "start": "00:00:52.870",
                        "end": "00:00:53.030"
                    },
                    {
                        "word": "个",
                        "start": "00:00:53.030",
                        "end": "00:00:53.270"
                    },
                    {
                        "word": "呃",
                        "start": "00:00:53.570",
                        "end": "00:00:53.810"
                    },
                    {
                        "word": "视",
                        "start": "00:00:53.850",
                        "end": "00:00:53.990"
                    },
                    {
                        "word": "频",
                        "start": "00:00:53.990",
                        "end": "00:00:54.190"
                    },
                    {
                        "word": "里",
                        "start": "00:00:54.190",
                        "end": "00:00:54.290"
                    },
                    {
                        "word": "面",
                        "start": "00:00:54.290",
                        "end": "00:00:54.470"
                    },
                    {
                        "word": "的",
                        "start": "00:00:54.470",
                        "end": "00:00:54.610"
                    },
                    {
                        "word": "一",
                        "start": "00:00:54.610",
                        "end": "00:00:54.710"
                    },
                    {
                        "word": "个",
                        "start": "00:00:54.710",
                        "end": "00:00:54.850"
                    },
                    {
                        "word": "声",
                        "start": "00:00:54.850",
                        "end": "00:00:55.010"
                    },
                    {
                        "word": "音",
                        "start": "00:00:55.010",
                        "end": "00:00:55.250"
                    }
                ]
            },
            {
                "text": "然后现在我们啊来试一下啊,",
                "start": "00:00:55.490",
                "end": "00:00:58.190",
                "spk": 0,
                "word_info": [
                    {
                        "word": "然",
                        "start": "00:00:55.490",
                        "end": "00:00:55.670"
                    },
                    {
                        "word": "后",
                        "start": "00:00:55.670",
                        "end": "00:00:55.790"
                    },
                    {
                        "word": "现",
                        "start": "00:00:55.790",
                        "end": "00:00:55.910"
                    },
                    {
                        "word": "在",
                        "start": "00:00:55.910",
                        "end": "00:00:56.090"
                    },
                    {
                        "word": "我",
                        "start": "00:00:56.090",
                        "end": "00:00:56.170"
                    },
                    {
                        "word": "们",
                        "start": "00:00:56.170",
                        "end": "00:00:56.410"
                    },
                    {
                        "word": "啊",
                        "start": "00:00:56.750",
                        "end": "00:00:56.990"
                    },
                    {
                        "word": "来",
                        "start": "00:00:57.110",
                        "end": "00:00:57.349"
                    },
                    {
                        "word": "试",
                        "start": "00:00:57.510",
                        "end": "00:00:57.750"
                    },
                    {
                        "word": "一",
                        "start": "00:00:57.770",
                        "end": "00:00:57.870"
                    },
                    {
                        "word": "下",
                        "start": "00:00:57.870",
                        "end": "00:00:57.990"
                    },
                    {
                        "word": "啊",
                        "start": "00:00:57.990",
                        "end": "00:00:58.190"
                    }
                ]
            },
            {
                "text": "现在有一分钟的一个音频了,",
                "start": "00:00:58.190",
                "end": "00:01:00.330",
                "spk": 0,
                "word_info": [
                    {
                        "word": "现",
                        "start": "00:00:58.190",
                        "end": "00:00:58.290"
                    },
                    {
                        "word": "在",
                        "start": "00:00:58.290",
                        "end": "00:00:58.530"
                    },
                    {
                        "word": "有",
                        "start": "00:00:58.530",
                        "end": "00:00:58.770"
                    },
                    {
                        "word": "一",
                        "start": "00:00:58.770",
                        "end": "00:00:58.890"
                    },
                    {
                        "word": "分",
                        "start": "00:00:58.890",
                        "end": "00:00:59.070"
                    },
                    {
                        "word": "钟",
                        "start": "00:00:59.070",
                        "end": "00:00:59.310"
                    },
                    {
                        "word": "的",
                        "start": "00:00:59.310",
                        "end": "00:00:59.510"
                    },
                    {
                        "word": "一",
                        "start": "00:00:59.510",
                        "end": "00:00:59.670"
                    },
                    {
                        "word": "个",
                        "start": "00:00:59.670",
                        "end": "00:00:59.910"
                    },
                    {
                        "word": "音",
                        "start": "00:00:59.930",
                        "end": "00:01:00.030"
                    },
                    {
                        "word": "频",
                        "start": "00:01:00.030",
                        "end": "00:01:00.210"
                    },
                    {
                        "word": "了",
                        "start": "00:01:00.210",
                        "end": "00:01:00.330"
                    }
                ]
            },
            {
                "text": "我们试一下吧。",
                "start": "00:01:00.330",
                "end": "00:01:00.960",
                "spk": 0,
                "word_info": [
                    {
                        "word": "我",
                        "start": "00:01:00.330",
                        "end": "00:01:00.410"
                    },
                    {
                        "word": "们",
                        "start": "00:01:00.410",
                        "end": "00:01:00.490"
                    },
                    {
                        "word": "试",
                        "start": "00:01:00.490",
                        "end": "00:01:00.590"
                    },
                    {
                        "word": "一",
                        "start": "00:01:00.590",
                        "end": "00:01:00.690"
                    },
                    {
                        "word": "下",
                        "start": "00:01:00.690",
                        "end": "00:01:00.810"
                    },
                    {
                        "word": "吧",
                        "start": "00:01:00.810",
                        "end": "00:01:00.960"
                    }
                ]
            }
        ]
    }
}

5. 支持区分说话人吗

支持的,可以看我上面发的json数据中有一个spk标识就是区分不同的说话人。那如果想要知道具体这个人是谁,就需要用到声纹对比了。这里可以看我之前的那个“会议录音转写系统”

6. 其它

点击这里查看博客
效果演示视频
🌍:lukeewin01
公众号:编程分享录
B站:编程分享录

Logo

腾讯云面向开发者汇聚海量精品云计算使用和开发经验,营造开放的云计算技术生态圈。

更多推荐