Diogo-V's picture
Upload results for wav2vec
1a3bafa verified
| | 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_2 | wav2vec | nlr_t_cos | 534.743 | 1692.4 | 0 | 18.8471 | 1 |
| 1 | 0 | 5 | 0 | librispeech | comb_2 | wav2vec | nlr_t_cos | 534.743 | 1692.4 | 0 | 18.8471 | 1 |
| 2 | 0 | 6 | 0 | librispeech | comb_2 | wav2vec | nlr_t_cos | 534.743 | 1692.4 | 0 | 18.8471 | 1 |
| 3 | 0 | 7 | 0 | librispeech | comb_2 | wav2vec | nlr_t_cos | 534.743 | 1692.4 | 0 | 18.8471 | 1 |
| 4 | 0 | 8 | 0 | librispeech | comb_2 | wav2vec | nlr_t_cos | 534.743 | 1692.4 | 0 | 18.8471 | 1 |
| 5 | 0 | 4 | 0 | librispeech | comb_6 | wav2vec | nlr_t_cos | 534.743 | 1692.4 | 0 | 19.4566 | 1 |
| 6 | 0 | 5 | 0 | librispeech | comb_6 | wav2vec | nlr_t_cos | 534.743 | 1692.4 | 0 | 19.4566 | 1 |
| 7 | 0 | 6 | 0 | librispeech | comb_6 | wav2vec | nlr_t_cos | 534.743 | 1692.4 | 0 | 19.4566 | 1 |
| 8 | 0 | 7 | 0 | librispeech | comb_6 | wav2vec | nlr_t_cos | 534.743 | 1692.4 | 0 | 19.4566 | 1 |
| 9 | 0 | 8 | 0 | librispeech | comb_6 | wav2vec | nlr_t_cos | 534.743 | 1692.4 | 0 | 19.4566 | 1 |
| 10 | 0 | 4 | 0 | librispeech | comb_16 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 22.2552 | 1 |
| 11 | 0 | 5 | 0 | librispeech | comb_16 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 22.2552 | 1 |
| 12 | 0 | 6 | 0 | librispeech | comb_16 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 22.2552 | 1 |
| 13 | 0 | 7 | 0 | librispeech | comb_16 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 22.2552 | 1 |
| 14 | 0 | 8 | 0 | librispeech | comb_16 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 22.2552 | 1 |
| 15 | 0 | 4 | 0 | librispeech | comb_4 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 22.9867 | 1 |
| 16 | 0 | 5 | 0 | librispeech | comb_4 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 22.9867 | 1 |
| 17 | 0 | 6 | 0 | librispeech | comb_4 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 22.9867 | 1 |
| 18 | 0 | 7 | 0 | librispeech | comb_4 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 22.9867 | 1 |
| 19 | 0 | 8 | 0 | librispeech | comb_4 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 22.9867 | 1 |
| 20 | 0 | 4 | 0 | librispeech | comb_9 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 25.481 | 1 |
| 21 | 0 | 5 | 0 | librispeech | comb_9 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 25.481 | 1 |
| 22 | 0 | 6 | 0 | librispeech | comb_9 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 25.481 | 1 |
| 23 | 0 | 7 | 0 | librispeech | comb_9 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 25.481 | 1 |
| 24 | 0 | 8 | 0 | librispeech | comb_9 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 25.481 | 1 |
| 25 | 0 | 4 | 0 | librispeech | comb_7 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 27.7123 | 1 |
| 26 | 0 | 5 | 0 | librispeech | comb_7 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 27.7123 | 1 |
| 27 | 0 | 6 | 0 | librispeech | comb_7 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 27.7123 | 1 |
| 28 | 0 | 7 | 0 | librispeech | comb_7 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 27.7123 | 1 |
| 29 | 0 | 8 | 0 | librispeech | comb_7 | wav2vec | nlr_t_cos | 535.632 | 1692.4 | 0 | 27.7123 | 1 |
| 30 | 0 | 4 | 0 | librispeech | comb_14 | wav2vec | nlr_t_cos | 368.001 | 1700.79 | 0 | 0.033001 | 1 |
| 31 | 0 | 5 | 0 | librispeech | comb_14 | wav2vec | nlr_t_cos | 368.001 | 1700.79 | 0 | 0.033001 | 1 |
| 32 | 0 | 6 | 0 | librispeech | comb_14 | wav2vec | nlr_t_cos | 368.001 | 1700.79 | 0 | 0.033001 | 1 |
| 33 | 0 | 7 | 0 | librispeech | comb_14 | wav2vec | nlr_t_cos | 368.001 | 1700.79 | 0 | 0.033001 | 1 |
| 34 | 0 | 8 | 0 | librispeech | comb_14 | wav2vec | nlr_t_cos | 368.001 | 1700.79 | 0 | 0.033001 | 1 |
| 35 | 0 | 8 | 0 | librispeech | comb_6_t | wav2vec | nlr_t_cos | 543.263 | 1709.18 | 0 | 22.1998 | 1 |
| 36 | 0 | 8 | 0 | librispeech | comb_2_t | wav2vec | nlr_t_cos | 543.263 | 1713.37 | 0 | 83.2675 | 1 |
| 37 | 0 | 8 | 0 | librispeech | comb_16_t | wav2vec | nlr_t_cos | 544.152 | 1713.37 | 0 | 24.4086 | 1 |
| 38 | 0 | 8 | 0 | librispeech | comb_9_t | wav2vec | nlr_t_cos | 544.152 | 1713.37 | 0 | 29.9653 | 1 |
| 39 | 0 | 8 | 0 | librispeech | comb_4_t | wav2vec | nlr_t_cos | 544.152 | 1713.37 | 0 | 71.3977 | 1 |
| 40 | 0 | 8 | 0 | librispeech | comb_7_t | wav2vec | nlr_t_cos | 544.16 | 1713.37 | 0 | 81.0025 | 1 |
| 41 | 0 | 8 | 0 | librispeech | comb_14_t | wav2vec | nlr_t_cos | 376.653 | 1717.57 | 0 | 0.04261 | 1 |
| 42 | 0 | 8 | 0 | librispeech | ao_woq | wav2vec | fixed | 658.018 | 4890.56 | 0 | 19.9987 | 0.0239712 |
| 43 | 0 | 6 | 0 | librispeech | woq | wav2vec | fixed | 658.093 | 4890.56 | 0 | 19.6045 | 0.0234031 |
| 44 | 0 | 7 | 0 | librispeech | woq | wav2vec | fixed | 658.093 | 4890.56 | 0 | 19.6245 | 0.023608 |
| 45 | 0 | 5 | 0 | librispeech | woq | wav2vec | fixed | 658.093 | 4890.56 | 0 | 19.9956 | 0.0237326 |
| 46 | 0 | 4 | 0 | librispeech | woq | wav2vec | fixed | 658.093 | 4890.56 | 0 | 20.2496 | 0.0268908 |
| 47 | 0 | 8 | 0 | librispeech | woq | wav2vec | fixed | 658.093 | 4890.56 | 0 | 21.0567 | 0.0239495 |
| 48 | 0 | 6 | 0 | librispeech | comb_18 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 25.1446 | 0.0235391 |
| 49 | 0 | 5 | 0 | librispeech | comb_18 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 25.1639 | 0.0237636 |
| 50 | 0 | 6 | 0 | librispeech | comb_11 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 25.3564 | 0.0234952 |
| 51 | 0 | 4 | 0 | librispeech | comb_18 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 25.4863 | 0.0246974 |
| 52 | 0 | 8 | 0 | librispeech | comb_1 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 25.6042 | 0.0236692 |
| 53 | 0 | 7 | 0 | librispeech | comb_11 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 25.9423 | 0.0238367 |
| 54 | 0 | 4 | 0 | librispeech | comb_1 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 25.971 | 0.0270026 |
| 55 | 0 | 5 | 0 | librispeech | comb_1 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 26.0201 | 0.0244742 |
| 56 | 0 | 8 | 0 | librispeech | comb_17 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 26.176 | 0.0281612 |
| 57 | 0 | 5 | 0 | librispeech | comb_11 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 26.3176 | 0.023834 |
| 58 | 0 | 7 | 0 | librispeech | comb_1 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 26.5486 | 0.0238573 |
| 59 | 0 | 4 | 0 | librispeech | comb_11 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 26.5991 | 0.0298433 |
| 60 | 0 | 7 | 0 | librispeech | comb_18 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 27.1573 | 0.0236571 |
| 61 | 0 | 7 | 0 | librispeech | comb_5 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 28.0551 | 0.0238843 |
| 62 | 0 | 4 | 0 | librispeech | comb_5 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 28.191 | 0.0245219 |
| 63 | 0 | 5 | 0 | librispeech | comb_5 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 28.2432 | 0.0240672 |
| 64 | 0 | 8 | 0 | librispeech | comb_5 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 28.4908 | 0.0238565 |
| 65 | 0 | 8 | 0 | librispeech | comb_8 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 31.2521 | 0.0255521 |
| 66 | 0 | 6 | 0 | librispeech | comb_8 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 31.4069 | 0.0257202 |
| 67 | 0 | 5 | 0 | librispeech | comb_8 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 31.5004 | 0.0272731 |
| 68 | 0 | 4 | 0 | librispeech | comb_8 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 31.6789 | 0.0292721 |
| 69 | 0 | 7 | 0 | librispeech | comb_8 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 31.97 | 0.0258734 |
| 70 | 0 | 8 | 0 | librispeech | comb_18 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 39.6635 | 0.0240304 |
| 71 | 0 | 6 | 0 | librispeech | comb_1 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 67.6877 | 0.0234908 |
| 72 | 0 | 8 | 0 | librispeech | comb_11 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 67.8218 | 0.0241342 |
| 73 | 0 | 7 | 0 | librispeech | comb_17 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 68.8995 | 0.0295771 |
| 74 | 0 | 6 | 0 | librispeech | comb_5 | wav2vec | nlr_t_cos | 658.907 | 4890.56 | 0 | 105.494 | 0.0234656 |
| 75 | 0 | 8 | 0 | librispeech | woq_t | wav2vec | fixed | 666.612 | 4911.53 | 0 | 21.6051 | 0.0250778 |
| 76 | 0 | 6 | 0 | librispeech | woq_t | wav2vec | fixed | 666.612 | 4911.53 | 0 | 21.9569 | 0.0236406 |
| 77 | 0 | 4 | 0 | librispeech | woq_t | wav2vec | fixed | 666.612 | 4911.53 | 0 | 22.0088 | 0.02757 |
| 78 | 0 | 7 | 0 | librispeech | woq_t | wav2vec | fixed | 666.612 | 4911.53 | 0 | 22.1579 | 0.0256592 |
| 79 | 0 | 5 | 0 | librispeech | woq_t | wav2vec | fixed | 666.612 | 4911.53 | 0 | 24.7563 | 0.0249287 |
| 80 | 0 | 5 | 0 | librispeech | comb_18_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 27.0746 | 0.0245326 |
| 81 | 0 | 7 | 0 | librispeech | comb_18_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 27.1641 | 0.0258149 |
| 82 | 0 | 4 | 0 | librispeech | comb_11_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 27.2946 | 0.0306752 |
| 83 | 0 | 7 | 0 | librispeech | comb_11_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 27.8996 | 0.0246386 |
| 84 | 0 | 8 | 0 | librispeech | comb_18_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 27.9842 | 0.0256516 |
| 85 | 0 | 7 | 0 | librispeech | comb_1_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 28.0253 | 0.0258276 |
| 86 | 0 | 6 | 0 | librispeech | comb_18_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 28.201 | 0.0244089 |
| 87 | 0 | 5 | 0 | librispeech | comb_5_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 29.0477 | 0.0246485 |
| 88 | 0 | 6 | 0 | librispeech | comb_5_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 29.2805 | 0.0242187 |
| 89 | 0 | 4 | 0 | librispeech | comb_1_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 29.3779 | 0.0268453 |
| 90 | 0 | 6 | 0 | librispeech | comb_11_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 29.9897 | 0.0243625 |
| 91 | 0 | 4 | 0 | librispeech | comb_18_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 30.443 | 0.0252159 |
| 92 | 0 | 8 | 0 | librispeech | comb_17_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 30.5424 | 0.0280897 |
| 93 | 0 | 5 | 0 | librispeech | comb_11_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 30.635 | 0.0239284 |
| 94 | 0 | 6 | 0 | librispeech | comb_1_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 31.1242 | 0.0240568 |
| 95 | 0 | 7 | 0 | librispeech | comb_17_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 31.4272 | 0.0287043 |
| 96 | 0 | 5 | 0 | librispeech | comb_8_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 32.4574 | 0.0286654 |
| 97 | 0 | 5 | 0 | librispeech | comb_1_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 32.5917 | 0.0257096 |
| 98 | 0 | 4 | 0 | librispeech | comb_5_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 33.7322 | 0.0245612 |
| 99 | 0 | 6 | 0 | librispeech | comb_8_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 34.0684 | 0.0262312 |
| 100 | 0 | 4 | 0 | librispeech | comb_8_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 34.2649 | 0.0301296 |
| 101 | 0 | 7 | 0 | librispeech | comb_8_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 34.7261 | 0.028539 |
| 102 | 0 | 8 | 0 | librispeech | comb_11_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 38.225 | 0.0262214 |
| 103 | 0 | 8 | 0 | librispeech | comb_8_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 96.4344 | 0.0273185 |
| 104 | 0 | 7 | 0 | librispeech | comb_5_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 130.634 | 0.0253306 |
| 105 | 0 | 8 | 0 | librispeech | comb_5_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 131.95 | 0.0261157 |
| 106 | 0 | 8 | 0 | librispeech | comb_1_t | wav2vec | nlr_t_cos | 667.427 | 4911.53 | 0 | 133.954 | 0.0250669 |
| 107 | 0 | 32 | 0 | librispeech | base | wav2vec | ---- | 1564.77 | 5620.37 | 0 | 15.0918 | 0.0239474 |