{"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,请问好玩字幕软件,增加类似Enever 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。该视图操作跟Enever 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。木软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,哎呀,都是,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。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,再次识别该视频或者是同类的视频,就会准确地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。常见的愿选择是,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。点击导出内容,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。点击导出,打开说话人的SRT字幕文件了。点击导出,打开说话人的SRT字幕文件了。点击导出,打开说话人的SRT字幕文件了。点击导出,打开说话人的SRT字幕文件了。点击导出,打开说话人的SRT字幕文件了。点击导出,打开说话人的SRT字幕文件了。点击导出,打开说话人的SRT字幕文件了。点击导出,打开说话人的SRT字幕文件了。点击导出,打开说话人的SRT字幕文件了。", "segments": [{"id": 0, "seek": 0, "start": 0.0, "end": 7.32, "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。", "tokens": [50365, 12579, 6336, 119, 8861, 5233, 228, 18453, 8090, 21596, 4035, 11, 3111, 12949, 5233, 228, 18453, 7781, 40656, 39752, 1546, 22, 7549, 8090, 21596, 4035, 11, 3509, 114, 45456, 22381, 40211, 26613, 32150, 31429, 3919, 122, 8090, 21596, 4035, 41509, 6627, 5935, 110, 1543, 50731], "temperature": 0, "avg_logprob": -0.14884344060370264, "compression_ratio": 1.2825278810408922, "no_speech_prob": 6.883360634951652e-12}, {"id": 1, "seek": 0, "start": 8.22, "end": 14.76, "text": "不少小伙伴提建议,请问好玩字幕软件,增加类似Enever Labs的说话人识别功能。", "tokens": [50776, 1960, 15686, 7322, 7384, 247, 7384, 112, 20949, 34157, 7422, 106, 11, 27908, 22064, 2131, 19912, 22381, 40211, 17819, 107, 20485, 11, 24228, 252, 9990, 22113, 119, 7384, 120, 36, 716, 331, 40047, 1546, 8090, 21596, 4035, 5233, 228, 18453, 32311, 8225, 1543, 51103], "temperature": 0, "avg_logprob": -0.14884344060370264, "compression_ratio": 1.2825278810408922, "no_speech_prob": 6.883360634951652e-12}, {"id": 2, "seek": 0, "start": 15.26, "end": 19.04, "text": "新的版本已经加上了,接下来来看一下如何使用。", "tokens": [51128, 12560, 1546, 42096, 8802, 49161, 9990, 5708, 2289, 11, 14468, 4438, 6912, 6912, 28324, 43526, 22982, 9254, 1543, 51317], "temperature": 0, "avg_logprob": -0.14884344060370264, "compression_ratio": 1.2825278810408922, "no_speech_prob": 6.883360634951652e-12}, {"id": 3, "seek": 0, "start": 19.48, "end": 24.18, "text": "首先需要下载说话人识别模型,点击下载转入模型。", "tokens": [51339, 36490, 35748, 4438, 17819, 121, 8090, 21596, 4035, 5233, 228, 18453, 41908, 39823, 11, 12579, 6336, 119, 4438, 17819, 121, 17819, 105, 14028, 41908, 39823, 1543, 51574], "temperature": 0, "avg_logprob": -0.14884344060370264, "compression_ratio": 1.2825278810408922, "no_speech_prob": 6.883360634951652e-12}, {"id": 4, "seek": 2418, "start": 24.18, "end": 31.12, "text": "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。", "tokens": [50365, 2166, 12949, 18032, 36257, 7549, 12560, 1546, 8090, 21596, 4035, 5233, 228, 18453, 41908, 39823, 11, 20182, 1541, 19550, 38358, 41908, 39823, 11, 20182, 1541, 27869, 5233, 255, 940, 241, 38358, 41908, 39823, 1543, 50712], "temperature": 0, "avg_logprob": -0.11117385184928162, "compression_ratio": 1.4666666666666666, "no_speech_prob": 1.0257249043188477e-11}, {"id": 5, "seek": 2418, "start": 31.740000000000002, "end": 33.66, "text": "老用户点击下载即可。", "tokens": [50743, 10439, 9254, 1486, 115, 12579, 6336, 119, 4438, 17819, 121, 39127, 4429, 1543, 50839], "temperature": 0, "avg_logprob": -0.11117385184928162, "compression_ratio": 1.4666666666666666, "no_speech_prob": 1.0257249043188477e-11}, {"id": 6, "seek": 2418, "start": 34.1, "end": 40.4, "text": "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。", "tokens": [50861, 12560, 9254, 1486, 115, 44575, 11, 16233, 2166, 4438, 17819, 121, 17819, 105, 14028, 41908, 39823, 49873, 11, 29649, 6346, 237, 12949, 9722, 34961, 4438, 17819, 121, 19550, 38358, 8090, 21596, 4035, 5233, 228, 18453, 41908, 39823, 1543, 51176], "temperature": 0, "avg_logprob": -0.11117385184928162, "compression_ratio": 1.4666666666666666, "no_speech_prob": 1.0257249043188477e-11}, {"id": 7, "seek": 2418, "start": 40.82, "end": 44.06, "text": "这是一个蓝人杀的视频,共有7个说话人。", "tokens": [51197, 27455, 20182, 164, 26152, 4035, 4422, 222, 1546, 40656, 39752, 11, 15408, 2412, 22, 7549, 8090, 21596, 4035, 1543, 51359], "temperature": 0, "avg_logprob": -0.11117385184928162, "compression_ratio": 1.4666666666666666, "no_speech_prob": 1.0257249043188477e-11}, {"id": 8, "seek": 2418, "start": 44.5, "end": 47.18, "text": "先使用转入功能,转入出字幕。", "tokens": [51381, 10108, 22982, 9254, 17819, 105, 14028, 32311, 8225, 11, 17819, 105, 14028, 7781, 22381, 40211, 1543, 51515], "temperature": 0, "avg_logprob": -0.11117385184928162, "compression_ratio": 1.4666666666666666, "no_speech_prob": 1.0257249043188477e-11}, {"id": 9, "seek": 2418, "start": 51.379999999999995, "end": 53.22, "text": "可以切换到段落试图。", "tokens": [51725, 6723, 23632, 26075, 95, 4511, 28427, 30848, 5233, 243, 3919, 122, 1543, 51817], "temperature": 0, "avg_logprob": -0.11117385184928162, "compression_ratio": 1.4666666666666666, "no_speech_prob": 1.0257249043188477e-11}, {"id": 10, "seek": 5322, "start": 53.22, "end": 57.54, "text": "该视图操作跟Enever Labs的字幕编辑器很相似。", "tokens": [50365, 44646, 40656, 3919, 122, 13167, 235, 11914, 9678, 36, 716, 331, 40047, 1546, 22381, 40211, 38109, 244, 9830, 239, 34386, 4563, 15106, 7384, 120, 1543, 50581], "temperature": 0, "avg_logprob": -0.13679350444248745, "compression_ratio": 1.448559670781893, "no_speech_prob": 1.376147112930326e-11}, {"id": 11, "seek": 5322, "start": 58.22, "end": 63.78, "text": "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。", "tokens": [50615, 6723, 18032, 17944, 5233, 228, 18453, 8090, 21596, 4035, 32442, 11, 47123, 8090, 21596, 4035, 1546, 22381, 40211, 1541, 48640, 3581, 28427, 30848, 5975, 1546, 1543, 50893], "temperature": 0, "avg_logprob": -0.13679350444248745, "compression_ratio": 1.448559670781893, "no_speech_prob": 1.376147112930326e-11}, {"id": 12, "seek": 5322, "start": 64.53999999999999, "end": 68.02, "text": "点击识别说话人,要设置说话人的数量。", "tokens": [50931, 12579, 6336, 119, 5233, 228, 18453, 8090, 21596, 4035, 11, 4275, 7422, 122, 34719, 8090, 21596, 4035, 1546, 33188, 26748, 1543, 51105], "temperature": 0, "avg_logprob": -0.13679350444248745, "compression_ratio": 1.448559670781893, "no_speech_prob": 1.376147112930326e-11}, {"id": 13, "seek": 5322, "start": 68.48, "end": 71.0, "text": "你可以开启自动识别说话人的数量。", "tokens": [51128, 42766, 18937, 2392, 107, 9722, 34961, 5233, 228, 18453, 8090, 21596, 4035, 1546, 33188, 26748, 1543, 51254], "temperature": 0, "avg_logprob": -0.13679350444248745, "compression_ratio": 1.448559670781893, "no_speech_prob": 1.376147112930326e-11}, {"id": 14, "seek": 5322, "start": 71.34, "end": 74.72, "text": "木软已经开启了匹配已注册说话人的功能。", "tokens": [51271, 41437, 17819, 107, 49161, 18937, 2392, 107, 2289, 9937, 117, 38846, 15701, 26432, 5676, 234, 8090, 21596, 4035, 1546, 32311, 8225, 1543, 51440], "temperature": 0, "avg_logprob": -0.13679350444248745, "compression_ratio": 1.448559670781893, "no_speech_prob": 1.376147112930326e-11}, {"id": 15, "seek": 5322, "start": 75.3, "end": 78.12, "text": "点击这里可以查看已注册的说话人。", "tokens": [51469, 12579, 6336, 119, 35102, 6723, 42623, 4200, 15701, 26432, 5676, 234, 1546, 8090, 21596, 4035, 1543, 51610], "temperature": 0, "avg_logprob": -0.13679350444248745, "compression_ratio": 1.448559670781893, "no_speech_prob": 1.376147112930326e-11}, {"id": 16, "seek": 7812, "start": 78.12, "end": 83.62, "text": "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。", "tokens": [50365, 12579, 6336, 119, 3416, 100, 8082, 11, 10187, 18390, 2257, 12949, 22933, 11, 6723, 18032, 28427, 30848, 26613, 32150, 8090, 21596, 4035, 6627, 5935, 110, 41509, 2289, 1543, 50640], "temperature": 0, "avg_logprob": -0.371524362003102, "compression_ratio": 1.277511961722488, "no_speech_prob": 1.7853244924093126e-11}, {"id": 17, "seek": 7812, "start": 84.12, "end": 85.74000000000001, "text": "可以试听一下几个片段。", "tokens": [50665, 6723, 5233, 243, 31022, 8861, 6336, 254, 7549, 16668, 28427, 1543, 50746], "temperature": 0, "avg_logprob": -0.371524362003102, "compression_ratio": 1.277511961722488, "no_speech_prob": 1.7853244924093126e-11}, {"id": 18, "seek": 7812, "start": 86.44, "end": 89.14, "text": "天亮了,昨天晚上是个平安夜。", "tokens": [50781, 6135, 22991, 2289, 11, 47404, 6135, 50157, 1541, 7549, 16716, 16206, 30124, 1543, 50916], "temperature": 0, "avg_logprob": -0.371524362003102, "compression_ratio": 1.277511961722488, "no_speech_prob": 1.7853244924093126e-11}, {"id": 19, "seek": 7812, "start": 89.44, "end": 95.44, "text": "哎呀,都是,哎呀,都是,都照我,都说人都会照我。", "tokens": [50931, 26755, 15348, 11, 22796, 11, 26755, 15348, 11, 22796, 11, 7182, 32150, 1654, 11, 7182, 8090, 4035, 7182, 12949, 32150, 1654, 1543, 51231], "temperature": 0, "avg_logprob": -0.371524362003102, "compression_ratio": 1.277511961722488, "no_speech_prob": 1.7853244924093126e-11}, {"id": 20, "seek": 7812, "start": 95.58000000000001, "end": 97.12, "text": "昨天晚上为什么没叫我起来?", "tokens": [51238, 47404, 6135, 50157, 31006, 10062, 19855, 1654, 9147, 6912, 30, 51315], "temperature": 0, "avg_logprob": -0.371524362003102, "compression_ratio": 1.277511961722488, "no_speech_prob": 1.7853244924093126e-11}, {"id": 21, "seek": 7812, "start": 97.64, "end": 98.5, "text": "就很奇怪。", "tokens": [51341, 3111, 4563, 44082, 1543, 51384], "temperature": 0, "avg_logprob": -0.371524362003102, "compression_ratio": 1.277511961722488, "no_speech_prob": 1.7853244924093126e-11}, {"id": 22, "seek": 9850, "start": 98.5, "end": 104.22, "text": "可以看到分割是比较准确的,但是难免会有错误。", "tokens": [50365, 6723, 18032, 6627, 5935, 110, 1541, 11706, 9830, 225, 6336, 228, 38114, 106, 1546, 11, 11189, 46531, 2347, 235, 12949, 2412, 29900, 5233, 107, 1543, 50651], "temperature": 0, "avg_logprob": -0.10145612032908313, "compression_ratio": 1.3804347826086956, "no_speech_prob": 1.623879850032317e-11}, {"id": 23, "seek": 9850, "start": 104.54, "end": 107.62, "text": "比如这两人的声音很像,就没有准确的识别。", "tokens": [50667, 36757, 5562, 36257, 4035, 1546, 32045, 18034, 4563, 12760, 11, 3111, 17944, 6336, 228, 38114, 106, 1546, 5233, 228, 18453, 1543, 50821], "temperature": 0, "avg_logprob": -0.10145612032908313, "compression_ratio": 1.3804347826086956, "no_speech_prob": 1.623879850032317e-11}, {"id": 24, "seek": 9850, "start": 108.24, "end": 112.76, "text": "另外,语音句子比较短的情况下面,也会容易识别错误。", "tokens": [50852, 26202, 11, 5233, 255, 18034, 34592, 7626, 11706, 9830, 225, 5881, 255, 1546, 46514, 47150, 11, 6404, 12949, 49212, 5233, 228, 18453, 29900, 5233, 107, 1543, 51078], "temperature": 0, "avg_logprob": -0.10145612032908313, "compression_ratio": 1.3804347826086956, "no_speech_prob": 1.623879850032317e-11}, {"id": 25, "seek": 9850, "start": 113.14, "end": 116.22, "text": "号数会在未来的版本中持续优化准确率。", "tokens": [51097, 26987, 33188, 12949, 3581, 29954, 6912, 1546, 42096, 8802, 5975, 17694, 10115, 255, 7384, 246, 23756, 6336, 228, 38114, 106, 44866, 1543, 51251], "temperature": 0, "avg_logprob": -0.10145612032908313, "compression_ratio": 1.3804347826086956, "no_speech_prob": 1.623879850032317e-11}, {"id": 26, "seek": 9850, "start": 116.72, "end": 121.7, "text": "下一步就需要修改说话人,并将说话人注册到声文库中。", "tokens": [51276, 45271, 31429, 3111, 35748, 7792, 106, 34490, 8090, 21596, 4035, 11, 3509, 114, 45456, 8090, 21596, 4035, 26432, 5676, 234, 4511, 32045, 17174, 6346, 241, 5975, 1543, 51525], "temperature": 0, "avg_logprob": -0.10145612032908313, "compression_ratio": 1.3804347826086956, "no_speech_prob": 1.623879850032317e-11}, {"id": 27, "seek": 9850, "start": 122.5, "end": 126.38, "text": "点击说话人图标,这里可以修改说话人的名称。", "tokens": [51565, 12579, 6336, 119, 8090, 21596, 4035, 3919, 122, 162, 3921, 11, 35102, 6723, 7792, 106, 34490, 8090, 21596, 4035, 1546, 15940, 8204, 108, 1543, 51759], "temperature": 0, "avg_logprob": -0.10145612032908313, "compression_ratio": 1.3804347826086956, "no_speech_prob": 1.623879850032317e-11}, {"id": 28, "seek": 12638, "start": 126.38, "end": 133.12, "text": "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。", "tokens": [50365, 7792, 106, 34490, 13547, 11, 44646, 34592, 7626, 40282, 13547, 10115, 255, 44646, 8090, 21596, 4035, 1546, 34592, 7626, 11, 8090, 21596, 4035, 1546, 15940, 8204, 108, 7182, 12949, 23238, 7792, 106, 34490, 29327, 1543, 50702], "temperature": 0, "avg_logprob": -0.06706152433230553, "compression_ratio": 1.7735042735042734, "no_speech_prob": 1.5629024116559087e-11}, {"id": 29, "seek": 12638, "start": 133.74, "end": 139.42, "text": "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。", "tokens": [50733, 2166, 47935, 3581, 35102, 2215, 231, 6852, 102, 8090, 21596, 4035, 11, 47935, 3581, 35102, 2215, 231, 6852, 102, 15701, 26432, 5676, 234, 32045, 17174, 1546, 8090, 21596, 4035, 1543, 51017], "temperature": 0, "avg_logprob": -0.06706152433230553, "compression_ratio": 1.7735042735042734, "no_speech_prob": 1.5629024116559087e-11}, {"id": 30, "seek": 12638, "start": 139.64, "end": 144.04, "text": "点击注册说话人,会将说话人注册到声文库中。", "tokens": [51028, 12579, 6336, 119, 26432, 5676, 234, 8090, 21596, 4035, 11, 12949, 45456, 8090, 21596, 4035, 26432, 5676, 234, 4511, 32045, 17174, 6346, 241, 5975, 1543, 51248], "temperature": 0, "avg_logprob": -0.06706152433230553, "compression_ratio": 1.7735042735042734, "no_speech_prob": 1.5629024116559087e-11}, {"id": 31, "seek": 12638, "start": 144.6, "end": 150.85999999999999, "text": "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。", "tokens": [51276, 16233, 2166, 5233, 228, 18453, 8090, 21596, 4035, 49873, 11, 18937, 2392, 107, 9937, 117, 38846, 18937, 28053, 11, 3111, 12949, 9937, 117, 38846, 32045, 17174, 6346, 241, 5975, 1546, 8090, 21596, 4035, 2289, 1543, 51589], "temperature": 0, "avg_logprob": -0.06706152433230553, "compression_ratio": 1.7735042735042734, "no_speech_prob": 1.5629024116559087e-11}, {"id": 32, "seek": 12638, "start": 151.44, "end": 156.35999999999999, "text": "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。", "tokens": [51618, 42766, 3581, 7422, 122, 34719, 5975, 25085, 4511, 8090, 21596, 4035, 7422, 122, 34719, 11, 6723, 18032, 15701, 26432, 5676, 234, 1546, 8090, 21596, 4035, 1543, 51864], "temperature": 0, "avg_logprob": -0.06706152433230553, "compression_ratio": 1.7735042735042734, "no_speech_prob": 1.5629024116559087e-11}, {"id": 33, "seek": 15638, "start": 156.38, "end": 161.18, "text": "注意,不同的说话人识别模型,声文库是不通用的。", "tokens": [50365, 40794, 11, 47123, 1546, 8090, 21596, 4035, 5233, 228, 18453, 41908, 39823, 11, 32045, 17174, 6346, 241, 1541, 1960, 19550, 9254, 1546, 1543, 50605], "temperature": 0, "avg_logprob": -0.11817343300635662, "compression_ratio": 1.3649289099526067, "no_speech_prob": 1.7354499781685462e-11}, {"id": 34, "seek": 15638, "start": 161.4, "end": 165.22, "text": "了解了操作,就可以完成整个视频字幕的说话人修改。", "tokens": [50616, 2289, 17278, 2289, 13167, 235, 11914, 11, 36781, 41509, 27662, 7549, 40656, 39752, 22381, 40211, 1546, 8090, 21596, 4035, 7792, 106, 34490, 1543, 50807], "temperature": 0, "avg_logprob": -0.11817343300635662, "compression_ratio": 1.3649289099526067, "no_speech_prob": 1.7354499781685462e-11}, {"id": 35, "seek": 15638, "start": 165.98, "end": 172.92, "text": "完成后,再次识别该视频或者是同类的视频,就会准确地识别出不同的说话人了。", "tokens": [50845, 41509, 13547, 11, 8623, 9487, 5233, 228, 18453, 44646, 40656, 39752, 31148, 1541, 13089, 22113, 119, 1546, 40656, 39752, 11, 3111, 12949, 6336, 228, 38114, 106, 10928, 5233, 228, 18453, 7781, 47123, 1546, 8090, 21596, 4035, 2289, 1543, 51192], "temperature": 0, "avg_logprob": -0.11817343300635662, "compression_ratio": 1.3649289099526067, "no_speech_prob": 1.7354499781685462e-11}, {"id": 36, "seek": 15638, "start": 173.34, "end": 176.22, "text": "那么如何过滤出不同说话人的字幕呢?", "tokens": [51213, 35693, 43526, 16866, 15868, 97, 7781, 47123, 8090, 21596, 4035, 1546, 22381, 40211, 6240, 30, 51357], "temperature": 0, "avg_logprob": -0.11817343300635662, "compression_ratio": 1.3649289099526067, "no_speech_prob": 1.7354499781685462e-11}, {"id": 37, "seek": 17622, "start": 176.22, "end": 179.02, "text": "点击这里的说话人选择框。", "tokens": [50365, 12579, 6336, 119, 35102, 1546, 8090, 21596, 4035, 2215, 231, 6852, 102, 21416, 228, 1543, 50505], "temperature": 0, "avg_logprob": -0.2141486906236218, "compression_ratio": 1.0763358778625953, "no_speech_prob": 1.6284683670986233e-11}, {"id": 38, "seek": 17622, "start": 179.02, "end": 181.9, "text": "你可以选择显示不同说话人的字幕。", "tokens": [50505, 42766, 2215, 231, 6852, 102, 1431, 122, 25696, 47123, 8090, 21596, 4035, 1546, 22381, 40211, 1543, 50649], "temperature": 0, "avg_logprob": -0.2141486906236218, "compression_ratio": 1.0763358778625953, "no_speech_prob": 1.6284683670986233e-11}, {"id": 39, "seek": 17622, "start": 181.9, "end": 186.06, "text": "这个过滤操作在文稿章节试图也是生效的。", "tokens": [50649, 15368, 16866, 15868, 97, 13167, 235, 11914, 3581, 17174, 10415, 123, 11957, 254, 45161, 5233, 243, 3919, 122, 22021, 8244, 43076, 1546, 1543, 50857], "temperature": 0, "avg_logprob": -0.2141486906236218, "compression_ratio": 1.0763358778625953, "no_speech_prob": 1.6284683670986233e-11}, {"id": 40, "seek": 18606, "start": 186.06, "end": 190.36, "text": "常见的愿选择是,用户要复制出指定说话人的文稿。", "tokens": [50365, 11279, 23813, 1546, 4820, 123, 2215, 231, 6852, 102, 1541, 11, 9254, 1486, 115, 4275, 1787, 235, 25491, 7781, 25922, 12088, 8090, 21596, 4035, 1546, 17174, 10415, 123, 1543, 50580], "temperature": 0, "avg_logprob": -0.1805457392482893, "compression_ratio": 1.4755555555555555, "no_speech_prob": 1.6922706291833123e-11}, {"id": 41, "seek": 18606, "start": 192.66, "end": 198.34, "text": "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。", "tokens": [50695, 45669, 1960, 29955, 1431, 122, 25696, 45213, 44848, 940, 236, 1431, 122, 25696, 8090, 21596, 4035, 11, 6723, 12579, 35102, 1546, 36257, 7549, 18937, 28053, 1543, 50979], "temperature": 0, "avg_logprob": -0.1805457392482893, "compression_ratio": 1.4755555555555555, "no_speech_prob": 1.6922706291833123e-11}, {"id": 42, "seek": 18606, "start": 199.24, "end": 202.24, "text": "点击导出内容,就可以将文稿导出了。", "tokens": [51024, 12579, 6336, 119, 4510, 120, 7781, 34742, 25750, 11, 36781, 45456, 17174, 10415, 123, 4510, 120, 7781, 2289, 1543, 51174], "temperature": 0, "avg_logprob": -0.1805457392482893, "compression_ratio": 1.4755555555555555, "no_speech_prob": 1.6922706291833123e-11}, {"id": 43, "seek": 18606, "start": 203.54, "end": 206.54, "text": "如何导出带有说话人的SRT文件呢?", "tokens": [51239, 43526, 4510, 120, 7781, 4845, 99, 2412, 8090, 21596, 4035, 1546, 50, 49, 51, 17174, 20485, 6240, 30, 51389], "temperature": 0, "avg_logprob": -0.1805457392482893, "compression_ratio": 1.4755555555555555, "no_speech_prob": 1.6922706291833123e-11}, {"id": 44, "seek": 18606, "start": 206.94, "end": 209.52, "text": "点击导出,打开说话人开关。", "tokens": [51409, 12579, 6336, 119, 4510, 120, 7781, 11, 12467, 18937, 8090, 21596, 4035, 18937, 28053, 1543, 51538], "temperature": 0, "avg_logprob": -0.1805457392482893, "compression_ratio": 1.4755555555555555, "no_speech_prob": 1.6922706291833123e-11}, {"id": 45, "seek": 18606, "start": 210.06, "end": 213.46, "text": "即可导出带说话人的SRT字幕文件了。", "tokens": [51565, 39127, 4429, 4510, 120, 7781, 4845, 99, 8090, 21596, 4035, 1546, 50, 49, 51, 22381, 40211, 17174, 20485, 2289, 1543, 51735], "temperature": 0, "avg_logprob": -0.1805457392482893, "compression_ratio": 1.4755555555555555, "no_speech_prob": 1.6922706291833123e-11}, {"id": 46, "seek": 21346, "start": 213.46, "end": 215.46, "text": "点击导出,打开说话人的SRT字幕文件了。", "tokens": [50365, 12579, 6336, 119, 4510, 120, 7781, 11, 12467, 18937, 8090, 21596, 4035, 1546, 50, 49, 51, 22381, 40211, 17174, 20485, 2289, 1543, 50465], "temperature": 0, "avg_logprob": -0.27272557143138665, "compression_ratio": 6.814285714285714, "no_speech_prob": 5.635609756637905e-10}, {"id": 47, "seek": 21346, "start": 215.46, "end": 216.46, "text": "点击导出,打开说话人的SRT字幕文件了。", "tokens": [50465, 12579, 6336, 119, 4510, 120, 7781, 11, 12467, 18937, 8090, 21596, 4035, 1546, 50, 49, 51, 22381, 40211, 17174, 20485, 2289, 1543, 50515], "temperature": 0, "avg_logprob": -0.27272557143138665, "compression_ratio": 6.814285714285714, "no_speech_prob": 5.635609756637905e-10}, {"id": 48, "seek": 21346, "start": 216.46, "end": 217.46, "text": "点击导出,打开说话人的SRT字幕文件了。", "tokens": [50515, 12579, 6336, 119, 4510, 120, 7781, 11, 12467, 18937, 8090, 21596, 4035, 1546, 50, 49, 51, 22381, 40211, 17174, 20485, 2289, 1543, 50565], "temperature": 0, "avg_logprob": -0.27272557143138665, "compression_ratio": 6.814285714285714, "no_speech_prob": 5.635609756637905e-10}, {"id": 49, "seek": 21346, "start": 217.46, "end": 218.46, "text": "点击导出,打开说话人的SRT字幕文件了。", "tokens": [50565, 12579, 6336, 119, 4510, 120, 7781, 11, 12467, 18937, 8090, 21596, 4035, 1546, 50, 49, 51, 22381, 40211, 17174, 20485, 2289, 1543, 50615], "temperature": 0, "avg_logprob": -0.27272557143138665, "compression_ratio": 6.814285714285714, "no_speech_prob": 5.635609756637905e-10}, {"id": 50, "seek": 21346, "start": 218.46, "end": 220.46, "text": "点击导出,打开说话人的SRT字幕文件了。", "tokens": [50615, 12579, 6336, 119, 4510, 120, 7781, 11, 12467, 18937, 8090, 21596, 4035, 1546, 50, 49, 51, 22381, 40211, 17174, 20485, 2289, 1543, 50715], "temperature": 0, "avg_logprob": -0.27272557143138665, "compression_ratio": 6.814285714285714, "no_speech_prob": 5.635609756637905e-10}, {"id": 51, "seek": 21346, "start": 220.46, "end": 222.46, "text": "点击导出,打开说话人的SRT字幕文件了。", "tokens": [50715, 12579, 6336, 119, 4510, 120, 7781, 11, 12467, 18937, 8090, 21596, 4035, 1546, 50, 49, 51, 22381, 40211, 17174, 20485, 2289, 1543, 50815], "temperature": 0, "avg_logprob": -0.27272557143138665, "compression_ratio": 6.814285714285714, "no_speech_prob": 5.635609756637905e-10}, {"id": 52, "seek": 21346, "start": 222.46, "end": 223.46, "text": "点击导出,打开说话人的SRT字幕文件了。", "tokens": [50815, 12579, 6336, 119, 4510, 120, 7781, 11, 12467, 18937, 8090, 21596, 4035, 1546, 50, 49, 51, 22381, 40211, 17174, 20485, 2289, 1543, 50865], "temperature": 0, "avg_logprob": -0.27272557143138665, "compression_ratio": 6.814285714285714, "no_speech_prob": 5.635609756637905e-10}, {"id": 53, "seek": 21346, "start": 223.46, "end": 224.46, "text": "点击导出,打开说话人的SRT字幕文件了。", "tokens": [50865, 12579, 6336, 119, 4510, 120, 7781, 11, 12467, 18937, 8090, 21596, 4035, 1546, 50, 49, 51, 22381, 40211, 17174, 20485, 2289, 1543, 50915], "temperature": 0, "avg_logprob": -0.27272557143138665, "compression_ratio": 6.814285714285714, "no_speech_prob": 5.635609756637905e-10}, {"id": 54, "seek": 21346, "start": 224.46, "end": 225.46, "text": "点击导出,打开说话人的SRT字幕文件了。", "tokens": [50915, 12579, 6336, 119, 4510, 120, 7781, 11, 12467, 18937, 8090, 21596, 4035, 1546, 50, 49, 51, 22381, 40211, 17174, 20485, 2289, 1543, 50965], "temperature": 0, "avg_logprob": -0.27272557143138665, "compression_ratio": 6.814285714285714, "no_speech_prob": 5.635609756637905e-10}], "language": "zh"}