{"text": "点击一下识别说话人就会识别出视频的7个说话人并将字幕按照步图说话人完成分割不少小伙伴提建议期望好玩字幕软件增加类似Energy Labs的说话人识别功能新的版本已经加上了接下来来看一下如何使用首先需要下载说话人识别模型点击下载转入模型你会看到两个新的说话人识别模型一个是通院模型一个是英语专院模型老用户点击下载即可新用户的话当你下载转入模型的时候程序会自动下载通院说话人识别模型这是一个蓝人杀的视频共有7个说话人先使用转入功能转入出字幕可以切换到段落试图该试图操作跟Energy Labs的字幕编辑器很相似可以看到没有识别说话人之前不同说话人的字幕是混在段落中的点击识别说话人要设置说话人的数量你可以开启自动识别说话人的数量默认已经开启了匹配已注册说话人的功能点击这里可以查看已注册的说话人点击执行等待一会儿可以看到段落按照说话人分割完成了可以试听一下几个片段天亮了昨天晚上是个平安夜哎呀都是哎都照我都说人都会照我昨天晚上为什么没叫我起来就很奇怪从一号玩家开始发言可以看到分割是比较准确的但是难免会有错误比如这两人的声音很像就没有准确的识别另外语音句子比较短的情况下面也会容易识别错误号数会在未来的版本中持续优化准确率下一步就需要修改说话人并将说话人注册到声文库中点击说话人图标这里可以修改说话人的名称修改后该句子以及后续该说话人的句子说话人的名称都会被修改掉你也可以在这里选择说话人也可以在这里选择已注册声文的说话人点击注册说话人会将说话人注册到声文库中当你识别说话人的时候开启匹配开关就会匹配声文库中的说话人了你可以在设置中找到说话人设置可以看到已注册的说话人注意不同的说话人识别模型声文库是不通用的了解了操作就可以完成整个视频字幕的说话人修改完成后再次识别该视频或是同类的视频就会准确的识别出不同的说话人了那么如何过滤出不同说话人的字幕呢点击这里的说话人选择框你可以选择显示不同说话人的字幕这个过滤操作在文稿章节试图也是生效的常见的愿途是用户要复制出指定说话人的文稿如果你不希望显示开始时间与显示说话人可以点这里的两个开关点击导出类录就可以将文稿导出了如何导出带有说话人的srt 文件呢点击导出打开说话人开关即可导出带说话人的srt 字幕文件了", "segments": [{"id": 0, "seek": 0, "start": 0.0, "end": 1.56, "text": "点击一下识别说话人", "tokens": [50365, 12579, 6336, 119, 8861, 5233, 228, 18453, 8090, 21596, 4035, 50443], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 1, "seek": 0, "start": 1.56, "end": 4.14, "text": "就会识别出视频的7个说话人", "tokens": [50443, 3111, 12949, 5233, 228, 18453, 7781, 40656, 39752, 1546, 22, 7549, 8090, 21596, 4035, 50572], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 2, "seek": 0, "start": 4.14, "end": 7.34, "text": "并将字幕按照步图说话人完成分割", "tokens": [50572, 3509, 114, 45456, 22381, 40211, 26613, 32150, 31429, 3919, 122, 8090, 21596, 4035, 41509, 6627, 5935, 110, 50732], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 3, "seek": 0, "start": 7.34, "end": 9.82, "text": "不少小伙伴提建议", "tokens": [50732, 1960, 15686, 7322, 7384, 247, 7384, 112, 20949, 34157, 7422, 106, 50856], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 4, "seek": 0, "start": 9.82, "end": 11.48, "text": "期望好玩字幕软件", "tokens": [50856, 16786, 22694, 2131, 19912, 22381, 40211, 17819, 107, 20485, 50939], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 5, "seek": 0, "start": 11.48, "end": 14.82, "text": "增加类似Energy Labs的说话人识别功能", "tokens": [50939, 24228, 252, 9990, 22113, 119, 7384, 120, 36, 1193, 1480, 40047, 1546, 8090, 21596, 4035, 5233, 228, 18453, 32311, 8225, 51106], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 6, "seek": 0, "start": 14.82, "end": 17.0, "text": "新的版本已经加上了", "tokens": [51106, 12560, 1546, 42096, 8802, 49161, 9990, 5708, 2289, 51215], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 7, "seek": 0, "start": 17.0, "end": 19.06, "text": "接下来来看一下如何使用", "tokens": [51215, 14468, 4438, 6912, 6912, 28324, 43526, 22982, 9254, 51318], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 8, "seek": 0, "start": 19.06, "end": 21.96, "text": "首先需要下载说话人识别模型", "tokens": [51318, 36490, 35748, 4438, 17819, 121, 8090, 21596, 4035, 5233, 228, 18453, 41908, 39823, 51463], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 9, "seek": 0, "start": 21.96, "end": 24.2, "text": "点击下载转入模型", "tokens": [51463, 12579, 6336, 119, 4438, 17819, 121, 17819, 105, 14028, 41908, 39823, 51575], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 10, "seek": 0, "start": 24.2, "end": 27.2, "text": "你会看到两个新的说话人识别模型", "tokens": [51575, 2166, 12949, 18032, 36257, 7549, 12560, 1546, 8090, 21596, 4035, 5233, 228, 18453, 41908, 39823, 51725], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 11, "seek": 0, "start": 27.2, "end": 29.0, "text": "一个是通院模型", "tokens": [51725, 20182, 1541, 19550, 38358, 41908, 39823, 51815], "temperature": 0, "avg_logprob": -0.15430209750220888, "compression_ratio": 1.3693379790940767, "no_speech_prob": 2.5260755293077253e-11}, {"id": 12, "seek": 2900, "start": 29.0, "end": 31.16, "text": "一个是英语专院模型", "tokens": [50365, 20182, 1541, 27869, 5233, 255, 940, 241, 38358, 41908, 39823, 50473], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 13, "seek": 2900, "start": 31.16, "end": 33.86, "text": "老用户点击下载即可", "tokens": [50473, 10439, 9254, 1486, 115, 12579, 6336, 119, 4438, 17819, 121, 39127, 4429, 50608], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 14, "seek": 2900, "start": 33.86, "end": 34.94, "text": "新用户的话", "tokens": [50608, 12560, 9254, 1486, 115, 44575, 50662], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 15, "seek": 2900, "start": 34.94, "end": 36.980000000000004, "text": "当你下载转入模型的时候", "tokens": [50662, 16233, 2166, 4438, 17819, 121, 17819, 105, 14028, 41908, 39823, 49873, 50764], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 16, "seek": 2900, "start": 36.980000000000004, "end": 40.44, "text": "程序会自动下载通院说话人识别模型", "tokens": [50764, 29649, 6346, 237, 12949, 9722, 34961, 4438, 17819, 121, 19550, 38358, 8090, 21596, 4035, 5233, 228, 18453, 41908, 39823, 50937], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 17, "seek": 2900, "start": 40.44, "end": 42.42, "text": "这是一个蓝人杀的视频", "tokens": [50937, 27455, 20182, 164, 26152, 4035, 4422, 222, 1546, 40656, 39752, 51036], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 18, "seek": 2900, "start": 42.42, "end": 44.120000000000005, "text": "共有7个说话人", "tokens": [51036, 15408, 2412, 22, 7549, 8090, 21596, 4035, 51121], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 19, "seek": 2900, "start": 44.120000000000005, "end": 45.879999999999995, "text": "先使用转入功能", "tokens": [51121, 10108, 22982, 9254, 17819, 105, 14028, 32311, 8225, 51209], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 20, "seek": 2900, "start": 45.879999999999995, "end": 47.2, "text": "转入出字幕", "tokens": [51209, 17819, 105, 14028, 7781, 22381, 40211, 51275], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 21, "seek": 2900, "start": 47.2, "end": 53.260000000000005, "text": "可以切换到段落试图", "tokens": [51275, 6723, 23632, 26075, 95, 4511, 28427, 30848, 5233, 243, 3919, 122, 51578], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 22, "seek": 2900, "start": 53.260000000000005, "end": 57.54, "text": "该试图操作跟Energy Labs的字幕编辑器很相似", "tokens": [51578, 44646, 5233, 243, 3919, 122, 13167, 235, 11914, 9678, 36, 1193, 1480, 40047, 1546, 22381, 40211, 38109, 244, 9830, 239, 34386, 4563, 15106, 7384, 120, 51792], "temperature": 0, "avg_logprob": -0.1186382448351061, "compression_ratio": 1.2519685039370079, "no_speech_prob": 1.1805704851208798e-11}, {"id": 23, "seek": 5754, "start": 57.54, "end": 60.48, "text": "可以看到没有识别说话人之前", "tokens": [50365, 6723, 18032, 17944, 5233, 228, 18453, 8090, 21596, 4035, 32442, 50512], "temperature": 0, "avg_logprob": -0.14269637202357385, "compression_ratio": 1.550561797752809, "no_speech_prob": 1.712591873870295e-11}, {"id": 24, "seek": 5754, "start": 60.48, "end": 63.78, "text": "不同说话人的字幕是混在段落中的", "tokens": [50512, 47123, 8090, 21596, 4035, 1546, 22381, 40211, 1541, 48640, 3581, 28427, 30848, 5975, 1546, 50677], "temperature": 0, "avg_logprob": -0.14269637202357385, "compression_ratio": 1.550561797752809, "no_speech_prob": 1.712591873870295e-11}, {"id": 25, "seek": 5754, "start": 63.78, "end": 65.92, "text": "点击识别说话人", "tokens": [50677, 12579, 6336, 119, 5233, 228, 18453, 8090, 21596, 4035, 50784], "temperature": 0, "avg_logprob": -0.14269637202357385, "compression_ratio": 1.550561797752809, "no_speech_prob": 1.712591873870295e-11}, {"id": 26, "seek": 5754, "start": 65.92, "end": 68.06, "text": "要设置说话人的数量", "tokens": [50784, 4275, 7422, 122, 34719, 8090, 21596, 4035, 1546, 33188, 26748, 50891], "temperature": 0, "avg_logprob": -0.14269637202357385, "compression_ratio": 1.550561797752809, "no_speech_prob": 1.712591873870295e-11}, {"id": 27, "seek": 5754, "start": 68.06, "end": 71.06, "text": "你可以开启自动识别说话人的数量", "tokens": [50891, 42766, 18937, 2392, 107, 9722, 34961, 5233, 228, 18453, 8090, 21596, 4035, 1546, 33188, 26748, 51041], "temperature": 0, "avg_logprob": -0.14269637202357385, "compression_ratio": 1.550561797752809, "no_speech_prob": 1.712591873870295e-11}, {"id": 28, "seek": 5754, "start": 71.06, "end": 74.78, "text": "默认已经开启了匹配已注册说话人的功能", "tokens": [51041, 6173, 246, 7422, 97, 49161, 18937, 2392, 107, 2289, 9937, 117, 38846, 15701, 26432, 5676, 234, 8090, 21596, 4035, 1546, 32311, 8225, 51227], "temperature": 0, "avg_logprob": -0.14269637202357385, "compression_ratio": 1.550561797752809, "no_speech_prob": 1.712591873870295e-11}, {"id": 29, "seek": 5754, "start": 74.78, "end": 78.18, "text": "点击这里可以查看已注册的说话人", "tokens": [51227, 12579, 6336, 119, 35102, 6723, 42623, 4200, 15701, 26432, 5676, 234, 1546, 8090, 21596, 4035, 51397], "temperature": 0, "avg_logprob": -0.14269637202357385, "compression_ratio": 1.550561797752809, "no_speech_prob": 1.712591873870295e-11}, {"id": 30, "seek": 7818, "start": 78.18, "end": 80.18, "text": "点击执行等待一会儿", "tokens": [50365, 12579, 6336, 119, 3416, 100, 8082, 10187, 18390, 2257, 12949, 22933, 50465], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 31, "seek": 7818, "start": 80.18, "end": 83.42, "text": "可以看到段落按照说话人分割完成了", "tokens": [50465, 6723, 18032, 28427, 30848, 26613, 32150, 8090, 21596, 4035, 6627, 5935, 110, 41509, 2289, 50627], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 32, "seek": 7818, "start": 83.42, "end": 85.62, "text": "可以试听一下几个片段", "tokens": [50627, 6723, 5233, 243, 31022, 8861, 6336, 254, 7549, 16668, 28427, 50737], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 33, "seek": 7818, "start": 85.62, "end": 87.06, "text": "天亮了", "tokens": [50737, 6135, 22991, 2289, 50809], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 34, "seek": 7818, "start": 87.06, "end": 89.06, "text": "昨天晚上是个平安夜", "tokens": [50809, 47404, 6135, 50157, 1541, 7549, 16716, 16206, 30124, 50909], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 35, "seek": 7818, "start": 89.06, "end": 91.5, "text": "哎呀", "tokens": [50909, 26755, 15348, 51031], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 36, "seek": 7818, "start": 91.5, "end": 92.7, "text": "都是", "tokens": [51031, 22796, 51091], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 37, "seek": 7818, "start": 92.7, "end": 93.2, "text": "哎", "tokens": [51091, 26755, 51116], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 38, "seek": 7818, "start": 93.2, "end": 94.10000000000001, "text": "都照我", "tokens": [51116, 7182, 32150, 1654, 51161], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 39, "seek": 7818, "start": 94.10000000000001, "end": 95.06, "text": "都说人都会照我", "tokens": [51161, 7182, 8090, 4035, 7182, 12949, 32150, 1654, 51209], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 40, "seek": 7818, "start": 95.06, "end": 97.06, "text": "昨天晚上为什么没叫我起来", "tokens": [51209, 47404, 6135, 50157, 31006, 10062, 19855, 1654, 9147, 6912, 51309], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 41, "seek": 7818, "start": 97.06, "end": 98.5, "text": "就很奇怪", "tokens": [51309, 3111, 4563, 44082, 51381], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 42, "seek": 7818, "start": 98.5, "end": 100.06, "text": "从一号玩家开始发言", "tokens": [51381, 35630, 2257, 26987, 19912, 5155, 45213, 28926, 12009, 51459], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 43, "seek": 7818, "start": 100.06, "end": 102.18, "text": "可以看到分割是比较准确的", "tokens": [51459, 6723, 18032, 6627, 5935, 110, 1541, 11706, 9830, 225, 6336, 228, 38114, 106, 1546, 51565], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 44, "seek": 7818, "start": 102.18, "end": 103.94000000000001, "text": "但是难免会有错误", "tokens": [51565, 11189, 46531, 2347, 235, 12949, 2412, 29900, 5233, 107, 51653], "temperature": 0, "avg_logprob": -0.3843457539876302, "compression_ratio": 1.3264462809917354, "no_speech_prob": 1.899212904998837e-11}, {"id": 45, "seek": 10394, "start": 103.94, "end": 107.78, "text": "比如这两人的声音很像就没有准确的识别", "tokens": [50365, 36757, 5562, 36257, 4035, 1546, 32045, 18034, 4563, 12760, 3111, 17944, 6336, 228, 38114, 106, 1546, 5233, 228, 18453, 50557], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 46, "seek": 10394, "start": 107.78, "end": 110.82, "text": "另外语音句子比较短的情况下面", "tokens": [50557, 26202, 5233, 255, 18034, 34592, 7626, 11706, 9830, 225, 5881, 255, 1546, 46514, 47150, 50709], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 47, "seek": 10394, "start": 110.82, "end": 112.82, "text": "也会容易识别错误", "tokens": [50709, 6404, 12949, 49212, 5233, 228, 18453, 29900, 5233, 107, 50809], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 48, "seek": 10394, "start": 112.82, "end": 116.42, "text": "号数会在未来的版本中持续优化准确率", "tokens": [50809, 26987, 33188, 12949, 3581, 29954, 6912, 1546, 42096, 8802, 5975, 17694, 10115, 255, 7384, 246, 23756, 6336, 228, 38114, 106, 44866, 50989], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 49, "seek": 10394, "start": 116.42, "end": 118.82, "text": "下一步就需要修改说话人", "tokens": [50989, 45271, 31429, 3111, 35748, 7792, 106, 34490, 8090, 21596, 4035, 51109], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 50, "seek": 10394, "start": 118.82, "end": 121.86, "text": "并将说话人注册到声文库中", "tokens": [51109, 3509, 114, 45456, 8090, 21596, 4035, 26432, 5676, 234, 4511, 32045, 17174, 6346, 241, 5975, 51261], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 51, "seek": 10394, "start": 121.86, "end": 124.02, "text": "点击说话人图标", "tokens": [51261, 12579, 6336, 119, 8090, 21596, 4035, 3919, 122, 162, 3921, 51369], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 52, "seek": 10394, "start": 124.02, "end": 126.5, "text": "这里可以修改说话人的名称", "tokens": [51369, 35102, 6723, 7792, 106, 34490, 8090, 21596, 4035, 1546, 15940, 8204, 108, 51493], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 53, "seek": 10394, "start": 126.5, "end": 127.62, "text": "修改后", "tokens": [51493, 7792, 106, 34490, 13547, 51549], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 54, "seek": 10394, "start": 127.62, "end": 130.66, "text": "该句子以及后续该说话人的句子", "tokens": [51549, 44646, 34592, 7626, 40282, 13547, 10115, 255, 44646, 8090, 21596, 4035, 1546, 34592, 7626, 51701], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 55, "seek": 10394, "start": 130.66, "end": 133.26, "text": "说话人的名称都会被修改掉", "tokens": [51701, 8090, 21596, 4035, 1546, 15940, 8204, 108, 7182, 12949, 23238, 7792, 106, 34490, 29327, 51831], "temperature": 0, "avg_logprob": -0.1261800398309547, "compression_ratio": 1.465648854961832, "no_speech_prob": 1.6514777392839797e-11}, {"id": 56, "seek": 13326, "start": 133.26, "end": 135.82, "text": "你也可以在这里选择说话人", "tokens": [50365, 2166, 47935, 3581, 35102, 2215, 231, 6852, 102, 8090, 21596, 4035, 50493], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 57, "seek": 13326, "start": 135.82, "end": 139.5, "text": "也可以在这里选择已注册声文的说话人", "tokens": [50493, 47935, 3581, 35102, 2215, 231, 6852, 102, 15701, 26432, 5676, 234, 32045, 17174, 1546, 8090, 21596, 4035, 50677], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 58, "seek": 13326, "start": 139.5, "end": 141.1, "text": "点击注册说话人", "tokens": [50677, 12579, 6336, 119, 26432, 5676, 234, 8090, 21596, 4035, 50757], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 59, "seek": 13326, "start": 141.1, "end": 144.14, "text": "会将说话人注册到声文库中", "tokens": [50757, 12949, 45456, 8090, 21596, 4035, 26432, 5676, 234, 4511, 32045, 17174, 6346, 241, 5975, 50909], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 60, "seek": 13326, "start": 144.14, "end": 146.38, "text": "当你识别说话人的时候", "tokens": [50909, 16233, 2166, 5233, 228, 18453, 8090, 21596, 4035, 49873, 51021], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 61, "seek": 13326, "start": 146.38, "end": 148.14, "text": "开启匹配开关", "tokens": [51021, 18937, 2392, 107, 9937, 117, 38846, 18937, 28053, 51109], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 62, "seek": 13326, "start": 148.14, "end": 150.94, "text": "就会匹配声文库中的说话人了", "tokens": [51109, 3111, 12949, 9937, 117, 38846, 32045, 17174, 6346, 241, 5975, 1546, 8090, 21596, 4035, 2289, 51249], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 63, "seek": 13326, "start": 150.94, "end": 154.22, "text": "你可以在设置中找到说话人设置", "tokens": [51249, 42766, 3581, 7422, 122, 34719, 5975, 25085, 4511, 8090, 21596, 4035, 7422, 122, 34719, 51413], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 64, "seek": 13326, "start": 154.22, "end": 156.62, "text": "可以看到已注册的说话人", "tokens": [51413, 6723, 18032, 15701, 26432, 5676, 234, 1546, 8090, 21596, 4035, 51533], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 65, "seek": 13326, "start": 156.62, "end": 159.42, "text": "注意不同的说话人识别模型", "tokens": [51533, 40794, 47123, 1546, 8090, 21596, 4035, 5233, 228, 18453, 41908, 39823, 51673], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 66, "seek": 13326, "start": 159.42, "end": 161.18, "text": "声文库是不通用的", "tokens": [51673, 32045, 17174, 6346, 241, 1541, 1960, 19550, 9254, 1546, 51761], "temperature": 0, "avg_logprob": -0.09918404257060676, "compression_ratio": 1.811881188118812, "no_speech_prob": 1.6713996506267925e-11}, {"id": 67, "seek": 16118, "start": 161.18, "end": 163.74, "text": "了解了操作就可以完成整个视频", "tokens": [50365, 2289, 17278, 2289, 13167, 235, 11914, 36781, 41509, 27662, 7549, 40656, 39752, 50493], "temperature": 0, "avg_logprob": -0.1232156919396442, "compression_ratio": 1.5238095238095237, "no_speech_prob": 2.055356926322638e-11}, {"id": 68, "seek": 16118, "start": 163.74, "end": 165.66, "text": "字幕的说话人修改", "tokens": [50493, 22381, 40211, 1546, 8090, 21596, 4035, 7792, 106, 34490, 50589], "temperature": 0, "avg_logprob": -0.1232156919396442, "compression_ratio": 1.5238095238095237, "no_speech_prob": 2.055356926322638e-11}, {"id": 69, "seek": 16118, "start": 165.66, "end": 169.82, "text": "完成后再次识别该视频或是同类的视频", "tokens": [50589, 41509, 13547, 8623, 9487, 5233, 228, 18453, 44646, 40656, 39752, 19780, 1541, 13089, 22113, 119, 1546, 40656, 39752, 50797], "temperature": 0, "avg_logprob": -0.1232156919396442, "compression_ratio": 1.5238095238095237, "no_speech_prob": 2.055356926322638e-11}, {"id": 70, "seek": 16118, "start": 169.82, "end": 173.1, "text": "就会准确的识别出不同的说话人了", "tokens": [50797, 3111, 12949, 6336, 228, 38114, 106, 1546, 5233, 228, 18453, 7781, 47123, 1546, 8090, 21596, 4035, 2289, 50961], "temperature": 0, "avg_logprob": -0.1232156919396442, "compression_ratio": 1.5238095238095237, "no_speech_prob": 2.055356926322638e-11}, {"id": 71, "seek": 16118, "start": 173.1, "end": 176.46, "text": "那么如何过滤出不同说话人的字幕呢", "tokens": [50961, 35693, 43526, 16866, 15868, 97, 7781, 47123, 8090, 21596, 4035, 1546, 22381, 40211, 6240, 51129], "temperature": 0, "avg_logprob": -0.1232156919396442, "compression_ratio": 1.5238095238095237, "no_speech_prob": 2.055356926322638e-11}, {"id": 72, "seek": 16118, "start": 176.46, "end": 178.94, "text": "点击这里的说话人选择框", "tokens": [51129, 12579, 6336, 119, 35102, 1546, 8090, 21596, 4035, 2215, 231, 6852, 102, 21416, 228, 51253], "temperature": 0, "avg_logprob": -0.1232156919396442, "compression_ratio": 1.5238095238095237, "no_speech_prob": 2.055356926322638e-11}, {"id": 73, "seek": 16118, "start": 178.94, "end": 182.06, "text": "你可以选择显示不同说话人的字幕", "tokens": [51253, 42766, 2215, 231, 6852, 102, 1431, 122, 25696, 47123, 8090, 21596, 4035, 1546, 22381, 40211, 51409], "temperature": 0, "avg_logprob": -0.1232156919396442, "compression_ratio": 1.5238095238095237, "no_speech_prob": 2.055356926322638e-11}, {"id": 74, "seek": 18206, "start": 182.06, "end": 186.54, "text": "这个过滤操作在文稿章节试图也是生效的", "tokens": [50365, 15368, 16866, 15868, 97, 13167, 235, 11914, 3581, 17174, 10415, 123, 11957, 254, 45161, 5233, 243, 3919, 122, 22021, 8244, 43076, 1546, 50589], "temperature": 0, "avg_logprob": -0.08675870528587928, "compression_ratio": 0.8307692307692308, "no_speech_prob": 1.9842462742336586e-11}, {"id": 75, "seek": 18654, "start": 186.54, "end": 191.01999999999998, "text": "常见的愿途是用户要复制出指定说话人的文稿", "tokens": [50365, 11279, 23813, 1546, 4820, 123, 2215, 242, 1541, 9254, 1486, 115, 4275, 1787, 235, 25491, 7781, 25922, 12088, 8090, 21596, 4035, 1546, 17174, 10415, 123, 50589], "temperature": 0, "avg_logprob": -0.1973029375076294, "compression_ratio": 1.3383838383838385, "no_speech_prob": 2.2201169722069203e-11}, {"id": 76, "seek": 18654, "start": 191.01999999999998, "end": 196.62, "text": "如果你不希望显示开始时间与显示说话人", "tokens": [50589, 45669, 1960, 29955, 1431, 122, 25696, 45213, 44848, 940, 236, 1431, 122, 25696, 8090, 21596, 4035, 50869], "temperature": 0, "avg_logprob": -0.1973029375076294, "compression_ratio": 1.3383838383838385, "no_speech_prob": 2.2201169722069203e-11}, {"id": 77, "seek": 18654, "start": 196.62, "end": 198.62, "text": "可以点这里的两个开关", "tokens": [50869, 6723, 12579, 35102, 1546, 36257, 7549, 18937, 28053, 50969], "temperature": 0, "avg_logprob": -0.1973029375076294, "compression_ratio": 1.3383838383838385, "no_speech_prob": 2.2201169722069203e-11}, {"id": 78, "seek": 18654, "start": 198.62, "end": 202.45999999999998, "text": "点击导出类录就可以将文稿导出了", "tokens": [50969, 12579, 6336, 119, 4510, 120, 7781, 22113, 119, 7391, 243, 36781, 45456, 17174, 10415, 123, 4510, 120, 7781, 2289, 51161], "temperature": 0, "avg_logprob": -0.1973029375076294, "compression_ratio": 1.3383838383838385, "no_speech_prob": 2.2201169722069203e-11}, {"id": 79, "seek": 18654, "start": 202.45999999999998, "end": 207.01999999999998, "text": "如何导出带有说话人的srt 文件呢", "tokens": [51161, 43526, 4510, 120, 7781, 4845, 99, 2412, 8090, 21596, 4035, 1546, 82, 17721, 220, 17174, 20485, 6240, 51389], "temperature": 0, "avg_logprob": -0.1973029375076294, "compression_ratio": 1.3383838383838385, "no_speech_prob": 2.2201169722069203e-11}, {"id": 80, "seek": 18654, "start": 207.01999999999998, "end": 209.89999999999998, "text": "点击导出打开说话人开关", "tokens": [51389, 12579, 6336, 119, 4510, 120, 7781, 12467, 18937, 8090, 21596, 4035, 18937, 28053, 51533], "temperature": 0, "avg_logprob": -0.1973029375076294, "compression_ratio": 1.3383838383838385, "no_speech_prob": 2.2201169722069203e-11}, {"id": 81, "seek": 20990, "start": 209.9, "end": 213.5, "text": "即可导出带说话人的srt 字幕文件了", "tokens": [50365, 39127, 4429, 4510, 120, 7781, 4845, 99, 8090, 21596, 4035, 1546, 82, 17721, 220, 22381, 40211, 17174, 20485, 2289, 50545], "temperature": 0, "avg_logprob": -0.21495132012800736, "compression_ratio": 0.8070175438596491, "no_speech_prob": 1.8935223181082428e-11}], "language": "zh"}