| | accuracy | bits | clip | dataset | method | model | params | peak_mem_alloc_mb | peak_mem_reserv_mb | perplexity | time_ms | wer | |----:|-----------:|-------:|-------:|:------------|:----------|:--------|:----------|--------------------:|---------------------:|-------------:|-----------:|----------:| | 0 | 0 | 4 | 0 | librispeech | comb_7 | wav2vec | nlr_t_lin | 534.743 | 1633.68 | 0 | 27.8148 | 1 | | 1 | 0 | 5 | 0 | librispeech | comb_7 | wav2vec | nlr_t_lin | 534.743 | 1633.68 | 0 | 27.8148 | 1 | | 2 | 0 | 6 | 0 | librispeech | comb_7 | wav2vec | nlr_t_lin | 534.743 | 1633.68 | 0 | 27.8148 | 1 | | 3 | 0 | 7 | 0 | librispeech | comb_7 | wav2vec | nlr_t_lin | 534.743 | 1633.68 | 0 | 27.8148 | 1 | | 4 | 0 | 8 | 0 | librispeech | comb_7 | wav2vec | nlr_t_lin | 534.743 | 1633.68 | 0 | 27.8148 | 1 | | 5 | 0 | 4 | 0 | librispeech | comb_4 | wav2vec | nlr_t_lin | 534.743 | 1633.68 | 0 | 37.7273 | 1 | | 6 | 0 | 5 | 0 | librispeech | comb_4 | wav2vec | nlr_t_lin | 534.743 | 1633.68 | 0 | 37.7273 | 1 | | 7 | 0 | 6 | 0 | librispeech | comb_4 | wav2vec | nlr_t_lin | 534.743 | 1633.68 | 0 | 37.7273 | 1 | | 8 | 0 | 7 | 0 | librispeech | comb_4 | wav2vec | nlr_t_lin | 534.743 | 1633.68 | 0 | 37.7273 | 1 | | 9 | 0 | 8 | 0 | librispeech | comb_4 | wav2vec | nlr_t_lin | 534.743 | 1633.68 | 0 | 37.7273 | 1 | | 10 | 0 | 4 | 0 | librispeech | comb_17 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 32.0422 | 1 | | 11 | 0 | 5 | 0 | librispeech | comb_17 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 32.0422 | 1 | | 12 | 0 | 6 | 0 | librispeech | comb_17 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 32.0422 | 1 | | 13 | 0 | 7 | 0 | librispeech | comb_17 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 32.0422 | 1 | | 14 | 0 | 8 | 0 | librispeech | comb_17 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 32.0422 | 1 | | 15 | 0 | 4 | 0 | librispeech | comb_1 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 34.8728 | 1 | | 16 | 0 | 5 | 0 | librispeech | comb_1 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 34.8728 | 1 | | 17 | 0 | 4 | 0 | librispeech | comb_2 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 111.374 | 1 | | 18 | 0 | 5 | 0 | librispeech | comb_2 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 111.374 | 1 | | 19 | 0 | 6 | 0 | librispeech | comb_2 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 111.374 | 1 | | 20 | 0 | 7 | 0 | librispeech | comb_2 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 111.374 | 1 | | 21 | 0 | 8 | 0 | librispeech | comb_2 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 111.374 | 1 | | 22 | 0 | 4 | 0 | librispeech | comb_6 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 121.667 | 1 | | 23 | 0 | 5 | 0 | librispeech | comb_6 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 121.667 | 1 | | 24 | 0 | 6 | 0 | librispeech | comb_6 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 121.667 | 1 | | 25 | 0 | 7 | 0 | librispeech | comb_6 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 121.667 | 1 | | 26 | 0 | 8 | 0 | librispeech | comb_6 | wav2vec | nlr_t_lin | 535.632 | 1633.68 | 0 | 121.667 | 1 | | 27 | 0 | 4 | 0 | librispeech | comb_11 | wav2vec | nlr_t_lin | 368.001 | 1642.07 | 0 | 0.049394 | 1 | | 28 | 0 | 5 | 0 | librispeech | comb_11 | wav2vec | nlr_t_lin | 368.001 | 1642.07 | 0 | 0.049394 | 1 | | 29 | 0 | 6 | 0 | librispeech | comb_11 | wav2vec | nlr_t_lin | 368.001 | 1642.07 | 0 | 0.049394 | 1 | | 30 | 0 | 7 | 0 | librispeech | comb_11 | wav2vec | nlr_t_lin | 368.001 | 1642.07 | 0 | 0.049394 | 1 | | 31 | 0 | 8 | 0 | librispeech | comb_11 | wav2vec | nlr_t_lin | 368.001 | 1642.07 | 0 | 0.049394 | 1 | | 32 | 0 | 8 | 0 | librispeech | comb_7_t | wav2vec | nlr_t_lin | 543.263 | 1650.46 | 0 | 37.968 | 1 | | 33 | 0 | 8 | 0 | librispeech | comb_4_t | wav2vec | nlr_t_lin | 543.263 | 1654.65 | 0 | 126.593 | 1 | | 34 | 0 | 8 | 0 | librispeech | comb_6_t | wav2vec | nlr_t_lin | 544.152 | 1654.65 | 0 | 55.0258 | 1 | | 35 | 0 | 5 | 0 | librispeech | comb_1_t | wav2vec | nlr_t_lin | 544.152 | 1654.65 | 0 | 59.6142 | 1 | | 36 | 0 | 8 | 0 | librispeech | comb_2_t | wav2vec | nlr_t_lin | 544.152 | 1654.65 | 0 | 61.5988 | 1 | | 37 | 0 | 8 | 0 | librispeech | comb_17_t | wav2vec | nlr_t_lin | 544.152 | 1654.65 | 0 | 139.148 | 1 | | 38 | 0 | 8 | 0 | librispeech | comb_11_t | wav2vec | nlr_t_lin | 376.653 | 1658.85 | 0 | 0.069782 | 1 | | 39 | 0 | 8 | 0 | librispeech | comb_15_t | wav2vec | nlr_t_lin | 671.551 | 4724.88 | 0 | 101.678 | 0.0287032 | | 40 | 0 | 8 | 0 | librispeech | comb_15 | wav2vec | nlr_t_lin | 658.018 | 4829.74 | 0 | 25.6234 | 0.0238659 | | 41 | 0 | 7 | 0 | librispeech | comb_15 | wav2vec | nlr_t_lin | 658.018 | 4829.74 | 0 | 26.1562 | 0.02398 | | 42 | 0 | 6 | 0 | librispeech | comb_15 | wav2vec | nlr_t_lin | 658.018 | 4829.74 | 0 | 33.5202 | 0.0235441 | | 43 | 0 | 5 | 0 | librispeech | comb_15 | wav2vec | nlr_t_lin | 658.018 | 4829.74 | 0 | 40.9004 | 0.0235195 | | 44 | 0 | 4 | 0 | librispeech | comb_15 | wav2vec | nlr_t_lin | 658.018 | 4829.74 | 0 | 107.638 | 0.0261924 | | 45 | 0 | 8 | 0 | librispeech | woq | wav2vec | fixed | 658.093 | 4831.84 | 0 | 34.0541 | 0.0239495 | | 46 | 0 | 5 | 0 | librispeech | woq | wav2vec | fixed | 658.093 | 4831.84 | 0 | 35.4665 | 0.0237326 | | 47 | 0 | 6 | 0 | librispeech | woq | wav2vec | fixed | 658.093 | 4831.84 | 0 | 38.6328 | 0.0234031 | | 48 | 0 | 4 | 0 | librispeech | woq | wav2vec | fixed | 658.093 | 4831.84 | 0 | 107.707 | 0.0268908 | | 49 | 0 | 7 | 0 | librispeech | woq | wav2vec | fixed | 658.093 | 4831.84 | 0 | 112.778 | 0.023608 | | 50 | 0 | 8 | 0 | librispeech | comb_1 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 36.2118 | 0.0308344 | | 51 | 0 | 8 | 0 | librispeech | comb_12 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 38.6678 | 0.0239239 | | 52 | 0 | 8 | 0 | librispeech | comb_8 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 39.8882 | 0.0285161 | | 53 | 0 | 4 | 0 | librispeech | comb_8 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 40.435 | 0.0407949 | | 54 | 0 | 8 | 0 | librispeech | comb_3 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 41.651 | 0.0238702 | | 55 | 0 | 5 | 0 | librispeech | comb_5 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 43.985 | 0.0273819 | | 56 | 0 | 6 | 0 | librispeech | comb_18 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 48.3737 | 0.0235409 | | 57 | 0 | 4 | 0 | librispeech | comb_12 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 49.0833 | 0.0260671 | | 58 | 0 | 6 | 0 | librispeech | comb_3 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 49.6859 | 0.0235041 | | 59 | 0 | 5 | 0 | librispeech | comb_12 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 54.8932 | 0.0243595 | | 60 | 0 | 6 | 0 | librispeech | comb_5 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 57.3485 | 0.0272304 | | 61 | 0 | 8 | 0 | librispeech | comb_18 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 57.7205 | 0.0240826 | | 62 | 0 | 7 | 0 | librispeech | comb_8 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 59.4552 | 0.0282786 | | 63 | 0 | 4 | 0 | librispeech | comb_5 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 63.9388 | 0.0287574 | | 64 | 0 | 8 | 0 | librispeech | comb_10 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 75.6275 | 0.0235543 | | 65 | 0 | 7 | 0 | librispeech | comb_1 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 108 | 0.0283186 | | 66 | 0 | 7 | 0 | librispeech | comb_18 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 108.29 | 0.023975 | | 67 | 0 | 5 | 0 | librispeech | comb_18 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 114.197 | 0.0232703 | | 68 | 0 | 8 | 0 | librispeech | comb_5 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 115.246 | 0.0268117 | | 69 | 0 | 7 | 0 | librispeech | comb_3 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 116.667 | 0.0235298 | | 70 | 0 | 7 | 0 | librispeech | comb_12 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 118.075 | 0.0236384 | | 71 | 0 | 5 | 0 | librispeech | comb_8 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 118.338 | 0.0320625 | | 72 | 0 | 6 | 0 | librispeech | comb_1 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 120.23 | 0.717435 | | 73 | 0 | 6 | 0 | librispeech | comb_10 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 120.698 | 0.023799 | | 74 | 0 | 5 | 0 | librispeech | comb_10 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 122.462 | 0.0269795 | | 75 | 0 | 4 | 0 | librispeech | comb_3 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 122.955 | 0.0250541 | | 76 | 0 | 6 | 0 | librispeech | comb_8 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 124.222 | 0.0285158 | | 77 | 0 | 4 | 0 | librispeech | comb_18 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 125.827 | 0.0255337 | | 78 | 0 | 7 | 0 | librispeech | comb_5 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 127.407 | 0.0259407 | | 79 | 0 | 5 | 0 | librispeech | comb_3 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 127.958 | 0.0238327 | | 80 | 0 | 4 | 0 | librispeech | comb_10 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 130.054 | 0.0435092 | | 81 | 0 | 7 | 0 | librispeech | comb_10 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 131.588 | 0.0237755 | | 82 | 0 | 6 | 0 | librispeech | comb_12 | wav2vec | nlr_t_lin | 658.907 | 4831.84 | 0 | 132.288 | 0.0234803 | | 83 | 0 | 6 | 0 | librispeech | comb_15_t | wav2vec | nlr_t_lin | 666.537 | 4850.71 | 0 | 33.1539 | 0.0244347 | | 84 | 0 | 5 | 0 | librispeech | comb_15_t | wav2vec | nlr_t_lin | 666.537 | 4850.71 | 0 | 41.0316 | 0.0243054 | | 85 | 0 | 7 | 0 | librispeech | comb_15_t | wav2vec | nlr_t_lin | 666.537 | 4850.71 | 0 | 49.6374 | 0.0262594 | | 86 | 0 | 4 | 0 | librispeech | comb_15_t | wav2vec | nlr_t_lin | 666.537 | 4850.71 | 0 | 122.271 | 0.0261048 | | 87 | 0 | 4 | 0 | librispeech | woq_t | wav2vec | fixed | 666.612 | 4852.81 | 0 | 60.2805 | 0.0277147 | | 88 | 0 | 6 | 0 | librispeech | woq_t | wav2vec | fixed | 666.612 | 4852.81 | 0 | 119.345 | 0.0240538 | | 89 | 0 | 8 | 0 | librispeech | woq_t | wav2vec | fixed | 666.612 | 4852.81 | 0 | 123.737 | 0.0255988 | | 90 | 0 | 5 | 0 | librispeech | woq_t | wav2vec | fixed | 666.612 | 4852.81 | 0 | 124.497 | 0.0245901 | | 91 | 0 | 7 | 0 | librispeech | woq_t | wav2vec | fixed | 666.612 | 4852.81 | 0 | 128.425 | 0.0254408 | | 92 | 0 | 8 | 0 | librispeech | comb_18_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 44.9024 | 0.0254874 | | 93 | 0 | 6 | 0 | librispeech | comb_8_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 46.574 | 0.0327753 | | 94 | 0 | 6 | 0 | librispeech | comb_10_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 48.4201 | 0.0252379 | | 95 | 0 | 7 | 0 | librispeech | comb_5_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 49.6598 | 0.0279553 | | 96 | 0 | 5 | 0 | librispeech | comb_5_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 51.6787 | 0.0293963 | | 97 | 0 | 8 | 0 | librispeech | comb_1_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 51.786 | 0.0338822 | | 98 | 0 | 4 | 0 | librispeech | comb_18_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 54.4989 | 0.0251166 | | 99 | 0 | 7 | 0 | librispeech | comb_10_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 55.2357 | 0.0268925 | | 100 | 0 | 8 | 0 | librispeech | comb_8_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 56.487 | 0.029517 | | 101 | 0 | 6 | 0 | librispeech | comb_1_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 56.4935 | 0.0324686 | | 102 | 0 | 6 | 0 | librispeech | comb_3_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 56.93 | 0.0243126 | | 103 | 0 | 7 | 0 | librispeech | comb_1_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 57.8093 | 0.0310668 | | 104 | 0 | 7 | 0 | librispeech | comb_3_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 58.3662 | 0.025374 | | 105 | 0 | 5 | 0 | librispeech | comb_10_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 60.4306 | 0.0289243 | | 106 | 0 | 7 | 0 | librispeech | comb_8_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 63.4972 | 0.0290772 | | 107 | 0 | 5 | 0 | librispeech | comb_18_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 66.2215 | 0.0242603 | | 108 | 0 | 4 | 0 | librispeech | comb_3_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 66.3299 | 0.0252412 | | 109 | 0 | 4 | 0 | librispeech | comb_5_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 74.8128 | 0.0295313 | | 110 | 0 | 7 | 0 | librispeech | comb_12_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 84.4353 | 0.0254019 | | 111 | 0 | 8 | 0 | librispeech | comb_3_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 100.155 | 0.0250088 | | 112 | 0 | 8 | 0 | librispeech | comb_5_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 118.909 | 0.0296686 | | 113 | 0 | 6 | 0 | librispeech | comb_12_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 127.224 | 0.0235594 | | 114 | 0 | 4 | 0 | librispeech | comb_10_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 128.88 | 0.0411994 | | 115 | 0 | 4 | 0 | librispeech | comb_12_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 128.973 | 0.0260528 | | 116 | 0 | 8 | 0 | librispeech | comb_12_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 129.53 | 0.0259109 | | 117 | 0 | 7 | 0 | librispeech | comb_18_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 132.76 | 0.0264286 | | 118 | 0 | 5 | 0 | librispeech | comb_8_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 132.972 | 0.0332409 | | 119 | 0 | 6 | 0 | librispeech | comb_5_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 134.121 | 0.0280872 | | 120 | 0 | 5 | 0 | librispeech | comb_12_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 134.823 | 0.0252606 | | 121 | 0 | 8 | 0 | librispeech | comb_10_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 138.247 | 0.0254178 | | 122 | 0 | 4 | 0 | librispeech | comb_8_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 143.542 | 0.0405398 | | 123 | 0 | 6 | 0 | librispeech | comb_18_t | wav2vec | nlr_t_lin | 667.427 | 4852.81 | 0 | 146.549 | 0.0246319 | | 124 | 0 | 5 | 0 | librispeech | comb_3_t | wav2vec | nlr_t_lin | 668.209 | 4852.81 | 0 | 146.077 | 0.0243907 | | 125 | 0 | 8 | 0 | librispeech | ao_woq | wav2vec | fixed | 658.018 | 4890.56 | 0 | 34.8716 | 0.0239712 | | 126 | 0 | 32 | 0 | librispeech | base | wav2vec | ---- | 1564.77 | 5620.37 | 0 | 105.862 | 0.0239474 |