{"text": "哎,會議裡幾個人同時說話,普通語音識別的問題不只是聽不清,更是不知道該聽誰。如果你只需要其中一個人的文字,先把每個人都分離出來,未必是最直接的路。Xiaomi Cocktail ASR-1給出了另一個思路。先輸入一段目標人的參考聲音,再輸入單人或多人混合語音。參考聲音就像一把聲文鑰匙,模型直接只轉錄對應的說話人。機子說清了,先聽一組官方演示。第一段是目標人的參考聲音,第二段是帶識別的混合語音。我想註冊一下聲文,這是一條註冊音頻。人們設計AI配方的過程,本質上主要還是一個不斷試錯的過程。模型最後輸出的是,人們設計AI配方的過程,本質上主要還是一個不斷試錯的過程。這裡不是先分出每一路音頻,而是用參考聲音直接約束轉寫目標。聽到效果後,再看真實會議數據。官方報告中,這個模型在AM&SDM上的詞錯率是21.81%,在ElimitingFar上是20.63%,對比表裡都明顯低於直接處理混合語音的通用模型。但只會轉路還不夠,如果參考聲音的人根本沒在待識別音頻裡,模型應該保持沉默。下面再聽一組副樣本。嗨同學。嗨有關系。這組副樣本的官方結果是空。三個副樣本測試集上,句實率分別是79.59%,75.35%和68.54%,但句實不是100%,正樣本也有最高0.73%的物據率。選行時要同時看詞錯率、句實率和物據率。開始試跑,只需要四個依賴,兩段音頻和一次模型調用。準備一段目標人參考音頻和一段代識別音頻。輸入期望是16000赫兹聲道,成功後應該只返回目標人文本。再換一段不相關的參考聲音,預期結果是空。最後的選行結論很清楚,指定受訪者轉路,以登記用戶語音入口或多人環境跟踪固定說話人。他很對提。需要保留所有發言人的完整會議,就應該用說話人日誌或分離流程。官方示例使用約80億參數模型、CUDA和遠程自定義代碼,先做小樣本驗證再接入。這裡是智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。我們在智聲工坊。", "segments": [{"id": 0, "seek": 0, "start": 0.0, "end": 10.0, "text": "哎,會議裡幾個人同時說話,普通語音識別的問題不只是聽不清,更是不知道該聽誰。如果你只需要其中一個人的文字,先把每個人都分離出來,未必是最直接的路。", "tokens": [50365, 26755, 11, 6236, 24686, 11066, 23575, 40104, 13089, 6611, 4622, 11103, 11, 29993, 19550, 31348, 18034, 43143, 16158, 1546, 17197, 1960, 36859, 21524, 1960, 21784, 11, 19002, 1541, 17572, 22033, 21524, 20757, 1543, 45669, 14003, 35748, 9572, 5975, 8990, 4035, 1546, 17174, 22381, 11, 10108, 16075, 23664, 40104, 7182, 6627, 32662, 29741, 11, 29954, 28531, 1541, 8661, 43297, 1546, 24658, 1543, 50865], "temperature": 0, "avg_logprob": -0.11201262343776681, "compression_ratio": 1.4164456233421752, "no_speech_prob": 9.735798105203752e-12}, {"id": 1, "seek": 0, "start": 10.0, "end": 22.0, "text": "Xiaomi Cocktail ASR-1給出了另一個思路。先輸入一段目標人的參考聲音,再輸入單人或多人混合語音。參考聲音就像一把聲文鑰匙,模型直接只轉錄對應的說話人。", "tokens": [50865, 55, 654, 9220, 39410, 14430, 7469, 49, 12, 16, 17798, 7781, 2289, 22762, 8990, 8870, 24658, 1543, 10108, 12290, 116, 14028, 2257, 28427, 11386, 46299, 4035, 1546, 47375, 26504, 29454, 18034, 11, 8623, 12290, 116, 14028, 24227, 4035, 19780, 6392, 4035, 48640, 14245, 31348, 18034, 1543, 47375, 26504, 29454, 18034, 3111, 12760, 2257, 16075, 29454, 17174, 165, 239, 108, 9937, 247, 11, 41908, 39823, 43297, 14003, 32739, 9567, 226, 2855, 20481, 1546, 4622, 11103, 4035, 1543, 51465], "temperature": 0, "avg_logprob": -0.11201262343776681, "compression_ratio": 1.4164456233421752, "no_speech_prob": 9.735798105203752e-12}, {"id": 2, "seek": 0, "start": 22.0, "end": 29.0, "text": "機子說清了,先聽一組官方演示。第一段是目標人的參考聲音,第二段是帶識別的混合語音。", "tokens": [51465, 17543, 7626, 4622, 21784, 2289, 11, 10108, 21524, 2257, 30052, 31929, 9249, 31382, 25696, 1543, 18049, 28427, 1541, 11386, 46299, 4035, 1546, 47375, 26504, 29454, 18034, 11, 19693, 28427, 1541, 32379, 43143, 16158, 1546, 48640, 14245, 31348, 18034, 1543, 51815], "temperature": 0, "avg_logprob": -0.11201262343776681, "compression_ratio": 1.4164456233421752, "no_speech_prob": 9.735798105203752e-12}, {"id": 3, "seek": 3000, "start": 30.0, "end": 35.0, "text": "我想註冊一下聲文,這是一條註冊音頻。", "tokens": [50365, 25246, 5396, 119, 5676, 232, 8861, 29454, 17174, 11, 16600, 2257, 31106, 5396, 119, 5676, 232, 18034, 29940, 1543, 50615], "temperature": 0, "avg_logprob": -0.06891813116558528, "compression_ratio": 1.588235294117647, "no_speech_prob": 1.885463486728245e-11}, {"id": 4, "seek": 3000, "start": 35.0, "end": 41.0, "text": "人們設計AI配方的過程,本質上主要還是一個不斷試錯的過程。", "tokens": [50615, 4035, 4623, 39035, 30114, 48698, 38846, 9249, 1546, 8816, 29649, 11, 8802, 43450, 5708, 13557, 4275, 25583, 8990, 1960, 4307, 115, 22099, 13133, 1546, 8816, 29649, 1543, 50915], "temperature": 0, "avg_logprob": -0.06891813116558528, "compression_ratio": 1.588235294117647, "no_speech_prob": 1.885463486728245e-11}, {"id": 5, "seek": 3000, "start": 41.0, "end": 48.0, "text": "模型最後輸出的是,人們設計AI配方的過程,本質上主要還是一個不斷試錯的過程。", "tokens": [50915, 41908, 39823, 20578, 12290, 116, 7781, 24620, 11, 4035, 4623, 39035, 30114, 48698, 38846, 9249, 1546, 8816, 29649, 11, 8802, 43450, 5708, 13557, 4275, 25583, 8990, 1960, 4307, 115, 22099, 13133, 1546, 8816, 29649, 1543, 51265], "temperature": 0, "avg_logprob": -0.06891813116558528, "compression_ratio": 1.588235294117647, "no_speech_prob": 1.885463486728245e-11}, {"id": 6, "seek": 3000, "start": 48.0, "end": 53.0, "text": "這裡不是先分出每一路音頻,而是用參考聲音直接約束轉寫目標。", "tokens": [51265, 18771, 7296, 10108, 6627, 7781, 23664, 2257, 24658, 18034, 29940, 11, 11070, 1541, 9254, 47375, 26504, 29454, 18034, 43297, 30889, 44320, 32739, 4510, 104, 11386, 46299, 1543, 51515], "temperature": 0, "avg_logprob": -0.06891813116558528, "compression_ratio": 1.588235294117647, "no_speech_prob": 1.885463486728245e-11}, {"id": 7, "seek": 5300, "start": 53.0, "end": 67.0, "text": "聽到效果後,再看真實會議數據。官方報告中,這個模型在AM&SDM上的詞錯率是21.81%,在ElimitingFar上是20.63%,對比表裡都明顯低於直接處理混合語音的通用模型。", "tokens": [50365, 21524, 4511, 43076, 9319, 5661, 11, 8623, 4200, 6303, 10376, 6236, 24686, 30622, 36841, 1543, 31929, 9249, 17803, 16846, 5975, 11, 6287, 41908, 39823, 3581, 2865, 5, 23969, 44, 5708, 1546, 6716, 252, 13133, 44866, 1541, 4436, 13, 32875, 8923, 3581, 36, 4197, 1748, 37, 289, 5708, 1541, 2009, 13, 29491, 8923, 2855, 11706, 17571, 11066, 7182, 11100, 46605, 41377, 19488, 43297, 39289, 13876, 48640, 14245, 31348, 18034, 1546, 19550, 9254, 41908, 39823, 1543, 51065], "temperature": 0, "avg_logprob": -0.16579674451779097, "compression_ratio": 0.9950738916256158, "no_speech_prob": 2.0118370511190697e-11}, {"id": 8, "seek": 6700, "start": 67.0, "end": 74.0, "text": "但只會轉路還不夠,如果參考聲音的人根本沒在待識別音頻裡,模型應該保持沉默。", "tokens": [50365, 8395, 14003, 6236, 32739, 24658, 7824, 1960, 31649, 11, 13119, 47375, 26504, 29454, 18034, 29979, 31337, 8802, 4913, 3581, 18390, 43143, 16158, 18034, 29940, 11066, 11, 41908, 39823, 26087, 24302, 17694, 3308, 231, 6173, 246, 1543, 50715], "temperature": 0, "avg_logprob": -0.15461736525932368, "compression_ratio": 1.2153284671532847, "no_speech_prob": 2.001824921105122e-11}, {"id": 9, "seek": 6700, "start": 74.0, "end": 76.0, "text": "下面再聽一組副樣本。", "tokens": [50715, 47150, 8623, 21524, 2257, 30052, 5935, 107, 6180, 8802, 1543, 50815], "temperature": 0, "avg_logprob": -0.15461736525932368, "compression_ratio": 1.2153284671532847, "no_speech_prob": 2.001824921105122e-11}, {"id": 10, "seek": 6700, "start": 76.0, "end": 77.0, "text": "嗨同學。", "tokens": [50815, 6083, 101, 13089, 21372, 1543, 50865], "temperature": 0, "avg_logprob": -0.15461736525932368, "compression_ratio": 1.2153284671532847, "no_speech_prob": 2.001824921105122e-11}, {"id": 11, "seek": 6700, "start": 77.0, "end": 80.0, "text": "嗨有關系。", "tokens": [50865, 6083, 101, 2412, 14899, 25368, 1543, 51015], "temperature": 0, "avg_logprob": -0.15461736525932368, "compression_ratio": 1.2153284671532847, "no_speech_prob": 2.001824921105122e-11}, {"id": 12, "seek": 6700, "start": 80.0, "end": 82.0, "text": "這組副樣本的官方結果是空。", "tokens": [51015, 2664, 30052, 5935, 107, 6180, 8802, 1546, 31929, 9249, 35181, 1541, 23322, 1543, 51115], "temperature": 0, "avg_logprob": -0.15461736525932368, "compression_ratio": 1.2153284671532847, "no_speech_prob": 2.001824921105122e-11}, {"id": 13, "seek": 6700, "start": 82.0, "end": 93.0, "text": "三個副樣本測試集上,句實率分別是79.59%,75.35%和68.54%,但句實不是100%,正樣本也有最高0.73%的物據率。", "tokens": [51115, 10960, 3338, 5935, 107, 6180, 8802, 9592, 105, 22099, 26020, 5708, 11, 34592, 10376, 44866, 6627, 16158, 1541, 32042, 13, 19600, 8923, 11901, 13, 8794, 4, 12565, 27102, 13, 19563, 8923, 8395, 34592, 10376, 7296, 6879, 8923, 15789, 6180, 8802, 6404, 2412, 8661, 12979, 15, 13, 33396, 4, 1546, 23516, 36841, 44866, 1543, 51665], "temperature": 0, "avg_logprob": -0.15461736525932368, "compression_ratio": 1.2153284671532847, "no_speech_prob": 2.001824921105122e-11}, {"id": 14, "seek": 9300, "start": 93.0, "end": 97.0, "text": "選行時要同時看詞錯率、句實率和物據率。", "tokens": [50365, 21625, 8082, 6611, 4275, 13089, 6611, 4200, 6716, 252, 13133, 44866, 1231, 34592, 10376, 44866, 12565, 23516, 36841, 44866, 1543, 50565], "temperature": 0, "avg_logprob": -0.09947648094695749, "compression_ratio": 1.364321608040201, "no_speech_prob": 1.7557613349317158e-11}, {"id": 15, "seek": 9300, "start": 97.0, "end": 100.0, "text": "開始試跑,只需要四個依賴,兩段音頻和一次模型調用。", "tokens": [50565, 21017, 22099, 32585, 11, 14003, 35748, 19425, 3338, 3254, 251, 164, 7062, 11, 16313, 28427, 18034, 29940, 12565, 27505, 41908, 39823, 32943, 9254, 1543, 50715], "temperature": 0, "avg_logprob": -0.09947648094695749, "compression_ratio": 1.364321608040201, "no_speech_prob": 1.7557613349317158e-11}, {"id": 16, "seek": 9300, "start": 100.0, "end": 103.0, "text": "準備一段目標人參考音頻和一段代識別音頻。", "tokens": [50715, 36241, 2257, 28427, 11386, 46299, 4035, 47375, 26504, 18034, 29940, 12565, 2257, 28427, 19105, 43143, 16158, 18034, 29940, 1543, 50865], "temperature": 0, "avg_logprob": -0.09947648094695749, "compression_ratio": 1.364321608040201, "no_speech_prob": 1.7557613349317158e-11}, {"id": 17, "seek": 9300, "start": 103.0, "end": 107.0, "text": "輸入期望是16000赫兹聲道,成功後應該只返回目標人文本。", "tokens": [50865, 12290, 116, 14028, 16786, 22694, 1541, 6866, 1360, 5266, 104, 2347, 117, 29454, 6025, 11, 11336, 32311, 5661, 26087, 14003, 3316, 242, 8350, 11386, 46299, 4035, 17174, 8802, 1543, 51065], "temperature": 0, "avg_logprob": -0.09947648094695749, "compression_ratio": 1.364321608040201, "no_speech_prob": 1.7557613349317158e-11}, {"id": 18, "seek": 9300, "start": 107.0, "end": 110.0, "text": "再換一段不相關的參考聲音,預期結果是空。", "tokens": [51065, 8623, 36338, 2257, 28427, 1960, 15106, 14899, 1546, 47375, 26504, 29454, 18034, 11, 30156, 16786, 35181, 1541, 23322, 1543, 51215], "temperature": 0, "avg_logprob": -0.09947648094695749, "compression_ratio": 1.364321608040201, "no_speech_prob": 1.7557613349317158e-11}, {"id": 19, "seek": 9300, "start": 110.0, "end": 116.0, "text": "最後的選行結論很清楚,指定受訪者轉路,以登記用戶語音入口或多人環境跟踪固定說話人。", "tokens": [51215, 20578, 1546, 21625, 8082, 17144, 29340, 4563, 38433, 11, 25922, 12088, 23151, 5396, 103, 12444, 32739, 24658, 11, 3588, 25874, 16958, 9254, 1486, 114, 31348, 18034, 14028, 18144, 19780, 6392, 4035, 40063, 108, 47885, 9678, 41166, 103, 3919, 118, 12088, 4622, 11103, 4035, 1543, 51515], "temperature": 0, "avg_logprob": -0.09947648094695749, "compression_ratio": 1.364321608040201, "no_speech_prob": 1.7557613349317158e-11}, {"id": 20, "seek": 9300, "start": 116.0, "end": 117.0, "text": "他很對提。", "tokens": [51515, 5000, 4563, 2855, 20949, 1543, 51565], "temperature": 0, "avg_logprob": -0.09947648094695749, "compression_ratio": 1.364321608040201, "no_speech_prob": 1.7557613349317158e-11}, {"id": 21, "seek": 9300, "start": 117.0, "end": 121.0, "text": "需要保留所有發言人的完整會議,就應該用說話人日誌或分離流程。", "tokens": [51565, 35748, 24302, 24456, 39300, 14637, 12009, 4035, 1546, 14128, 27662, 6236, 24686, 11, 3111, 26087, 9254, 4622, 11103, 4035, 6890, 3549, 234, 19780, 6627, 32662, 27854, 29649, 1543, 51765], "temperature": 0, "avg_logprob": -0.09947648094695749, "compression_ratio": 1.364321608040201, "no_speech_prob": 1.7557613349317158e-11}, {"id": 22, "seek": 12100, "start": 121.0, "end": 127.0, "text": "官方示例使用約80億參數模型、CUDA和遠程自定義代碼,先做小樣本驗證再接入。", "tokens": [50365, 31929, 9249, 25696, 17797, 22982, 9254, 30889, 4702, 25459, 47375, 30622, 41908, 39823, 1231, 25864, 7509, 12565, 34489, 29649, 9722, 12088, 37430, 19105, 16337, 120, 11, 10108, 10907, 7322, 6180, 8802, 24023, 245, 11823, 231, 8623, 14468, 14028, 1543, 50665], "temperature": 0, "avg_logprob": -0.17029684561270256, "compression_ratio": 0.9202898550724637, "no_speech_prob": 2.0532789010707653e-11}, {"id": 23, "seek": 12100, "start": 127.0, "end": 128.0, "text": "這裡是智聲工坊。", "tokens": [50665, 18771, 1541, 5094, 118, 29454, 23323, 14872, 232, 1543, 50715], "temperature": 0, "avg_logprob": -0.17029684561270256, "compression_ratio": 0.9202898550724637, "no_speech_prob": 2.0532789010707653e-11}, {"id": 24, "seek": 12800, "start": 128.0, "end": 130.0, "text": "我們在智聲工坊。", "tokens": [50365, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50465], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 25, "seek": 12800, "start": 130.0, "end": 131.0, "text": "我們在智聲工坊。", "tokens": [50465, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50515], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 26, "seek": 12800, "start": 131.0, "end": 132.0, "text": "我們在智聲工坊。", "tokens": [50515, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50565], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 27, "seek": 12800, "start": 132.0, "end": 133.0, "text": "我們在智聲工坊。", "tokens": [50565, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50615], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 28, "seek": 12800, "start": 133.0, "end": 134.0, "text": "我們在智聲工坊。", "tokens": [50615, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50665], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 29, "seek": 12800, "start": 134.0, "end": 135.0, "text": "我們在智聲工坊。", "tokens": [50665, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50715], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 30, "seek": 12800, "start": 135.0, "end": 136.0, "text": "我們在智聲工坊。", "tokens": [50715, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50765], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 31, "seek": 12800, "start": 136.0, "end": 137.0, "text": "我們在智聲工坊。", "tokens": [50765, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50815], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 32, "seek": 12800, "start": 137.0, "end": 138.0, "text": "我們在智聲工坊。", "tokens": [50815, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50865], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 33, "seek": 12800, "start": 138.0, "end": 139.0, "text": "我們在智聲工坊。", "tokens": [50865, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50915], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 34, "seek": 12800, "start": 139.0, "end": 140.0, "text": "我們在智聲工坊。", "tokens": [50915, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 50965], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 35, "seek": 12800, "start": 140.0, "end": 141.0, "text": "我們在智聲工坊。", "tokens": [50965, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 51015], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 36, "seek": 12800, "start": 141.0, "end": 142.0, "text": "我們在智聲工坊。", "tokens": [51015, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 51065], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 37, "seek": 12800, "start": 142.0, "end": 143.0, "text": "我們在智聲工坊。", "tokens": [51065, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 51115], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 38, "seek": 12800, "start": 143.0, "end": 144.0, "text": "我們在智聲工坊。", "tokens": [51115, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 51165], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 39, "seek": 12800, "start": 144.0, "end": 145.0, "text": "我們在智聲工坊。", "tokens": [51165, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 51215], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 40, "seek": 12800, "start": 145.0, "end": 146.0, "text": "我們在智聲工坊。", "tokens": [51215, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 51265], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 41, "seek": 12800, "start": 146.0, "end": 147.0, "text": "我們在智聲工坊。", "tokens": [51265, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 51315], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 42, "seek": 12800, "start": 147.0, "end": 148.0, "text": "我們在智聲工坊。", "tokens": [51315, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 51365], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}, {"id": 43, "seek": 12800, "start": 148.0, "end": 149.0, "text": "我們在智聲工坊。", "tokens": [51365, 5884, 3581, 5094, 118, 29454, 23323, 14872, 232, 1543, 51415], "temperature": 0, "avg_logprob": -0.20211913446674432, "compression_ratio": 12.15, "no_speech_prob": 6.076185388170785e-11}], "language": "zh"}