{ "format": "inflect_v2_modern400_three_asr_v1", "prompt_count_per_system": 400, "total_audio_clips": 3200, "asr_models": { "qwen3_asr": "Qwen/Qwen3-ASR-1.7B", "nemotron35_asr": "nvidia/nemotron-3.5-asr-streaming-0.6b", "whisper_large_v3": "openai/whisper-large-v3" }, "macro_average": { "definition": "unweighted mean of the three corpus-level semantic WERs", "headline": false, "bootstrap": "matched-prompt resampling within each system", "samples": 10000 }, "systems": { "inflect-micro-v2": { "label": "Inflect-Micro-v2", "qwen3_asr": { "raw": { "utterances": 400, "errors": 159, "words": 6794, "wer": 0.023403002649396525 }, "raw_95ci": [ 0.017408416590977898, 0.030176415970287838 ], "semantic": { "utterances": 400, "errors": 172, "words": 6823, "wer": 0.02520885241096292 }, "semantic_95ci": [ 0.018783412801618264, 0.03235815602836879 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 0, "words": 296, "wer": 0.0 }, "semantic": { "utterances": 25, "errors": 0, "words": 309, "wer": 0.0 } }, "descriptive": { "raw": { "utterances": 16, "errors": 0, "words": 217, "wer": 0.0 }, "semantic": { "utterances": 16, "errors": 0, "words": 226, "wer": 0.0 } }, "emotional": { "raw": { "utterances": 24, "errors": 0, "words": 314, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 329, "wer": 0.0 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 114, "words": 4250, "wer": 0.026823529411764704 }, "semantic": { "utterances": 200, "errors": 148, "words": 4215, "wer": 0.035112692763938316 } }, "homographs": { "raw": { "utterances": 6, "errors": 0, "words": 70, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 70, "wer": 0.0 } }, "long": { "raw": { "utterances": 15, "errors": 1, "words": 412, "wer": 0.0024271844660194173 }, "semantic": { "utterances": 15, "errors": 1, "words": 432, "wer": 0.0023148148148148147 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 }, "semantic": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 } }, "narrative": { "raw": { "utterances": 24, "errors": 0, "words": 342, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 352, "wer": 0.0 } }, "numbers": { "raw": { "utterances": 6, "errors": 21, "words": 81, "wer": 0.25925925925925924 }, "semantic": { "utterances": 6, "errors": 4, "words": 64, "wer": 0.0625 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 }, "semantic": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 } }, "short": { "raw": { "utterances": 24, "errors": 3, "words": 98, "wer": 0.030612244897959183 }, "semantic": { "utterances": 24, "errors": 3, "words": 105, "wer": 0.02857142857142857 } }, "technical": { "raw": { "utterances": 21, "errors": 11, "words": 251, "wer": 0.043824701195219126 }, "semantic": { "utterances": 21, "errors": 7, "words": 256, "wer": 0.02734375 } } } }, "nemotron35_asr": { "raw": { "utterances": 400, "errors": 429, "words": 6794, "wer": 0.06314395054459818 }, "raw_95ci": [ 0.052087944518223406, 0.07540394973070018 ], "semantic": { "utterances": 400, "errors": 372, "words": 6823, "wer": 0.05452147149347794 }, "semantic_95ci": [ 0.04496430198997418, 0.0649688901750832 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 3, "words": 296, "wer": 0.010135135135135136 }, "semantic": { "utterances": 25, "errors": 3, "words": 309, "wer": 0.009708737864077669 } }, "descriptive": { "raw": { "utterances": 16, "errors": 2, "words": 217, "wer": 0.009216589861751152 }, "semantic": { "utterances": 16, "errors": 2, "words": 226, "wer": 0.008849557522123894 } }, "emotional": { "raw": { "utterances": 24, "errors": 3, "words": 314, "wer": 0.009554140127388535 }, "semantic": { "utterances": 24, "errors": 1, "words": 329, "wer": 0.00303951367781155 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 359, "words": 4250, "wer": 0.08447058823529412 }, "semantic": { "utterances": 200, "errors": 306, "words": 4215, "wer": 0.07259786476868327 } }, "homographs": { "raw": { "utterances": 6, "errors": 5, "words": 70, "wer": 0.07142857142857142 }, "semantic": { "utterances": 6, "errors": 5, "words": 70, "wer": 0.07142857142857142 } }, "long": { "raw": { "utterances": 15, "errors": 7, "words": 412, "wer": 0.01699029126213592 }, "semantic": { "utterances": 15, "errors": 6, "words": 432, "wer": 0.013888888888888888 } }, "long_range": { "raw": { "utterances": 6, "errors": 2, "words": 121, "wer": 0.01652892561983471 }, "semantic": { "utterances": 6, "errors": 2, "words": 121, "wer": 0.01652892561983471 } }, "names_places": { "raw": { "utterances": 6, "errors": 13, "words": 57, "wer": 0.22807017543859648 }, "semantic": { "utterances": 6, "errors": 13, "words": 57, "wer": 0.22807017543859648 } }, "narrative": { "raw": { "utterances": 24, "errors": 4, "words": 342, "wer": 0.011695906432748537 }, "semantic": { "utterances": 24, "errors": 4, "words": 352, "wer": 0.011363636363636364 } }, "numbers": { "raw": { "utterances": 6, "errors": 5, "words": 81, "wer": 0.06172839506172839 }, "semantic": { "utterances": 6, "errors": 4, "words": 64, "wer": 0.0625 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 }, "semantic": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 } }, "short": { "raw": { "utterances": 24, "errors": 6, "words": 98, "wer": 0.061224489795918366 }, "semantic": { "utterances": 24, "errors": 6, "words": 105, "wer": 0.05714285714285714 } }, "technical": { "raw": { "utterances": 21, "errors": 14, "words": 251, "wer": 0.055776892430278883 }, "semantic": { "utterances": 21, "errors": 14, "words": 256, "wer": 0.0546875 } } } }, "whisper_large_v3": { "raw": { "utterances": 400, "errors": 189, "words": 6794, "wer": 0.027818663526641155 }, "raw_95ci": [ 0.02115697588400651, 0.034870148818208345 ], "semantic": { "utterances": 400, "errors": 186, "words": 6823, "wer": 0.02726073574673897 }, "semantic_95ci": [ 0.020453534904401955, 0.03492018244013683 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 1, "words": 296, "wer": 0.0033783783783783786 }, "semantic": { "utterances": 25, "errors": 0, "words": 309, "wer": 0.0 } }, "descriptive": { "raw": { "utterances": 16, "errors": 2, "words": 217, "wer": 0.009216589861751152 }, "semantic": { "utterances": 16, "errors": 0, "words": 226, "wer": 0.0 } }, "emotional": { "raw": { "utterances": 24, "errors": 0, "words": 314, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 329, "wer": 0.0 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 124, "words": 4250, "wer": 0.029176470588235293 }, "semantic": { "utterances": 200, "errors": 154, "words": 4215, "wer": 0.0365361803084223 } }, "homographs": { "raw": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 }, "semantic": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 } }, "long": { "raw": { "utterances": 15, "errors": 1, "words": 412, "wer": 0.0024271844660194173 }, "semantic": { "utterances": 15, "errors": 1, "words": 432, "wer": 0.0023148148148148147 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 }, "semantic": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 } }, "narrative": { "raw": { "utterances": 24, "errors": 2, "words": 342, "wer": 0.005847953216374269 }, "semantic": { "utterances": 24, "errors": 1, "words": 352, "wer": 0.002840909090909091 } }, "numbers": { "raw": { "utterances": 6, "errors": 35, "words": 81, "wer": 0.43209876543209874 }, "semantic": { "utterances": 6, "errors": 10, "words": 64, "wer": 0.15625 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 }, "semantic": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 } }, "short": { "raw": { "utterances": 24, "errors": 4, "words": 98, "wer": 0.04081632653061224 }, "semantic": { "utterances": 24, "errors": 4, "words": 105, "wer": 0.0380952380952381 } }, "technical": { "raw": { "utterances": 21, "errors": 12, "words": 251, "wer": 0.04780876494023904 }, "semantic": { "utterances": 21, "errors": 8, "words": 256, "wer": 0.03125 } } } }, "asr_macro_average": { "wer": 0.03566368655039328, "wer_95ci": [ 0.02878832692497289, 0.04329524954900782 ] } }, "inflect-nano-v2": { "label": "Inflect-Nano-v2", "qwen3_asr": { "raw": { "utterances": 400, "errors": 179, "words": 6794, "wer": 0.026346776567559613 }, "raw_95ci": [ 0.020206362854686157, 0.033170442766178 ], "semantic": { "utterances": 400, "errors": 190, "words": 6823, "wer": 0.02784698812838927 }, "semantic_95ci": [ 0.021251648834823392, 0.0351635682374982 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 3, "words": 296, "wer": 0.010135135135135136 }, "semantic": { "utterances": 25, "errors": 1, "words": 309, "wer": 0.003236245954692557 } }, "descriptive": { "raw": { "utterances": 16, "errors": 1, "words": 217, "wer": 0.004608294930875576 }, "semantic": { "utterances": 16, "errors": 1, "words": 226, "wer": 0.004424778761061947 } }, "emotional": { "raw": { "utterances": 24, "errors": 0, "words": 314, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 329, "wer": 0.0 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 123, "words": 4250, "wer": 0.028941176470588234 }, "semantic": { "utterances": 200, "errors": 159, "words": 4215, "wer": 0.03772241992882562 } }, "homographs": { "raw": { "utterances": 6, "errors": 0, "words": 70, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 70, "wer": 0.0 } }, "long": { "raw": { "utterances": 15, "errors": 2, "words": 412, "wer": 0.0048543689320388345 }, "semantic": { "utterances": 15, "errors": 2, "words": 432, "wer": 0.004629629629629629 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 10, "words": 57, "wer": 0.17543859649122806 }, "semantic": { "utterances": 6, "errors": 8, "words": 57, "wer": 0.14035087719298245 } }, "narrative": { "raw": { "utterances": 24, "errors": 1, "words": 342, "wer": 0.0029239766081871343 }, "semantic": { "utterances": 24, "errors": 1, "words": 352, "wer": 0.002840909090909091 } }, "numbers": { "raw": { "utterances": 6, "errors": 20, "words": 81, "wer": 0.24691358024691357 }, "semantic": { "utterances": 6, "errors": 3, "words": 64, "wer": 0.046875 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 }, "semantic": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 } }, "short": { "raw": { "utterances": 24, "errors": 6, "words": 98, "wer": 0.061224489795918366 }, "semantic": { "utterances": 24, "errors": 6, "words": 105, "wer": 0.05714285714285714 } }, "technical": { "raw": { "utterances": 21, "errors": 10, "words": 251, "wer": 0.0398406374501992 }, "semantic": { "utterances": 21, "errors": 6, "words": 256, "wer": 0.0234375 } } } }, "nemotron35_asr": { "raw": { "utterances": 400, "errors": 461, "words": 6794, "wer": 0.06785398881365912 }, "raw_95ci": [ 0.05698005698005698, 0.07978646659933632 ], "semantic": { "utterances": 400, "errors": 384, "words": 6823, "wer": 0.056280228638428846 }, "semantic_95ci": [ 0.04723173515981735, 0.06624651912648395 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 8, "words": 296, "wer": 0.02702702702702703 }, "semantic": { "utterances": 25, "errors": 6, "words": 309, "wer": 0.019417475728155338 } }, "descriptive": { "raw": { "utterances": 16, "errors": 3, "words": 217, "wer": 0.013824884792626729 }, "semantic": { "utterances": 16, "errors": 3, "words": 226, "wer": 0.01327433628318584 } }, "emotional": { "raw": { "utterances": 24, "errors": 2, "words": 314, "wer": 0.006369426751592357 }, "semantic": { "utterances": 24, "errors": 2, "words": 329, "wer": 0.0060790273556231 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 377, "words": 4250, "wer": 0.08870588235294118 }, "semantic": { "utterances": 200, "errors": 303, "words": 4215, "wer": 0.07188612099644127 } }, "homographs": { "raw": { "utterances": 6, "errors": 8, "words": 70, "wer": 0.11428571428571428 }, "semantic": { "utterances": 6, "errors": 8, "words": 70, "wer": 0.11428571428571428 } }, "long": { "raw": { "utterances": 15, "errors": 3, "words": 412, "wer": 0.007281553398058253 }, "semantic": { "utterances": 15, "errors": 3, "words": 432, "wer": 0.006944444444444444 } }, "long_range": { "raw": { "utterances": 6, "errors": 3, "words": 121, "wer": 0.024793388429752067 }, "semantic": { "utterances": 6, "errors": 3, "words": 121, "wer": 0.024793388429752067 } }, "names_places": { "raw": { "utterances": 6, "errors": 12, "words": 57, "wer": 0.21052631578947367 }, "semantic": { "utterances": 6, "errors": 12, "words": 57, "wer": 0.21052631578947367 } }, "narrative": { "raw": { "utterances": 24, "errors": 10, "words": 342, "wer": 0.029239766081871343 }, "semantic": { "utterances": 24, "errors": 10, "words": 352, "wer": 0.028409090909090908 } }, "numbers": { "raw": { "utterances": 6, "errors": 4, "words": 81, "wer": 0.04938271604938271 }, "semantic": { "utterances": 6, "errors": 3, "words": 64, "wer": 0.046875 } }, "punctuation": { "raw": { "utterances": 6, "errors": 2, "words": 65, "wer": 0.03076923076923077 }, "semantic": { "utterances": 6, "errors": 2, "words": 65, "wer": 0.03076923076923077 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 }, "semantic": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 } }, "short": { "raw": { "utterances": 24, "errors": 13, "words": 98, "wer": 0.1326530612244898 }, "semantic": { "utterances": 24, "errors": 13, "words": 105, "wer": 0.12380952380952381 } }, "technical": { "raw": { "utterances": 21, "errors": 10, "words": 251, "wer": 0.0398406374501992 }, "semantic": { "utterances": 21, "errors": 10, "words": 256, "wer": 0.0390625 } } } }, "whisper_large_v3": { "raw": { "utterances": 400, "errors": 192, "words": 6794, "wer": 0.028260229614365615 }, "raw_95ci": [ 0.022173274596182086, 0.03481012658227848 ], "semantic": { "utterances": 400, "errors": 181, "words": 6823, "wer": 0.026527920269676094 }, "semantic_95ci": [ 0.020260492040520984, 0.03347280334728033 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 4, "words": 296, "wer": 0.013513513513513514 }, "semantic": { "utterances": 25, "errors": 1, "words": 309, "wer": 0.003236245954692557 } }, "descriptive": { "raw": { "utterances": 16, "errors": 1, "words": 217, "wer": 0.004608294930875576 }, "semantic": { "utterances": 16, "errors": 0, "words": 226, "wer": 0.0 } }, "emotional": { "raw": { "utterances": 24, "errors": 0, "words": 314, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 329, "wer": 0.0 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 118, "words": 4250, "wer": 0.02776470588235294 }, "semantic": { "utterances": 200, "errors": 142, "words": 4215, "wer": 0.03368920521945433 } }, "homographs": { "raw": { "utterances": 6, "errors": 4, "words": 70, "wer": 0.05714285714285714 }, "semantic": { "utterances": 6, "errors": 4, "words": 70, "wer": 0.05714285714285714 } }, "long": { "raw": { "utterances": 15, "errors": 2, "words": 412, "wer": 0.0048543689320388345 }, "semantic": { "utterances": 15, "errors": 2, "words": 432, "wer": 0.004629629629629629 } }, "long_range": { "raw": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 }, "semantic": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 } }, "names_places": { "raw": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 }, "semantic": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 } }, "narrative": { "raw": { "utterances": 24, "errors": 4, "words": 342, "wer": 0.011695906432748537 }, "semantic": { "utterances": 24, "errors": 3, "words": 352, "wer": 0.008522727272727272 } }, "numbers": { "raw": { "utterances": 6, "errors": 34, "words": 81, "wer": 0.41975308641975306 }, "semantic": { "utterances": 6, "errors": 8, "words": 64, "wer": 0.125 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 }, "semantic": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 } }, "short": { "raw": { "utterances": 24, "errors": 5, "words": 98, "wer": 0.05102040816326531 }, "semantic": { "utterances": 24, "errors": 5, "words": 105, "wer": 0.047619047619047616 } }, "technical": { "raw": { "utterances": 21, "errors": 12, "words": 251, "wer": 0.04780876494023904 }, "semantic": { "utterances": 21, "errors": 8, "words": 256, "wer": 0.03125 } } } }, "asr_macro_average": { "wer": 0.036885045678831406, "wer_95ci": [ 0.030208333333333334, 0.04434228798544271 ] } }, "kitten-nano-bruno": { "label": "KittenTTS Nano - Bruno", "qwen3_asr": { "raw": { "utterances": 400, "errors": 139, "words": 6794, "wer": 0.02045922873123344 }, "raw_95ci": [ 0.014941302027748132, 0.026771187694128087 ], "semantic": { "utterances": 400, "errors": 147, "words": 6823, "wer": 0.02154477502564854 }, "semantic_95ci": [ 0.015435835351089588, 0.0284862043251305 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 1, "words": 296, "wer": 0.0033783783783783786 }, "semantic": { "utterances": 25, "errors": 1, "words": 309, "wer": 0.003236245954692557 } }, "descriptive": { "raw": { "utterances": 16, "errors": 0, "words": 217, "wer": 0.0 }, "semantic": { "utterances": 16, "errors": 0, "words": 226, "wer": 0.0 } }, "emotional": { "raw": { "utterances": 24, "errors": 0, "words": 314, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 329, "wer": 0.0 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 94, "words": 4250, "wer": 0.02211764705882353 }, "semantic": { "utterances": 200, "errors": 125, "words": 4215, "wer": 0.02965599051008304 } }, "homographs": { "raw": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 }, "semantic": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 } }, "long": { "raw": { "utterances": 15, "errors": 1, "words": 412, "wer": 0.0024271844660194173 }, "semantic": { "utterances": 15, "errors": 1, "words": 432, "wer": 0.0023148148148148147 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 8, "words": 57, "wer": 0.14035087719298245 }, "semantic": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 } }, "narrative": { "raw": { "utterances": 24, "errors": 2, "words": 342, "wer": 0.005847953216374269 }, "semantic": { "utterances": 24, "errors": 2, "words": 352, "wer": 0.005681818181818182 } }, "numbers": { "raw": { "utterances": 6, "errors": 19, "words": 81, "wer": 0.2345679012345679 }, "semantic": { "utterances": 6, "errors": 2, "words": 64, "wer": 0.03125 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 }, "semantic": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 } }, "short": { "raw": { "utterances": 24, "errors": 1, "words": 98, "wer": 0.01020408163265306 }, "semantic": { "utterances": 24, "errors": 1, "words": 105, "wer": 0.009523809523809525 } }, "technical": { "raw": { "utterances": 21, "errors": 9, "words": 251, "wer": 0.035856573705179286 }, "semantic": { "utterances": 21, "errors": 5, "words": 256, "wer": 0.01953125 } } } }, "nemotron35_asr": { "raw": { "utterances": 400, "errors": 300, "words": 6794, "wer": 0.044156608772446274 }, "raw_95ci": [ 0.03619243784022363, 0.052726998035957096 ], "semantic": { "utterances": 400, "errors": 270, "words": 6823, "wer": 0.03957203576139528 }, "semantic_95ci": [ 0.03191024333381903, 0.04806156526789604 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 2, "words": 296, "wer": 0.006756756756756757 }, "semantic": { "utterances": 25, "errors": 2, "words": 309, "wer": 0.006472491909385114 } }, "descriptive": { "raw": { "utterances": 16, "errors": 1, "words": 217, "wer": 0.004608294930875576 }, "semantic": { "utterances": 16, "errors": 1, "words": 226, "wer": 0.004424778761061947 } }, "emotional": { "raw": { "utterances": 24, "errors": 7, "words": 314, "wer": 0.022292993630573247 }, "semantic": { "utterances": 24, "errors": 7, "words": 329, "wer": 0.02127659574468085 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 243, "words": 4250, "wer": 0.057176470588235294 }, "semantic": { "utterances": 200, "errors": 214, "words": 4215, "wer": 0.050771055753262156 } }, "homographs": { "raw": { "utterances": 6, "errors": 3, "words": 70, "wer": 0.04285714285714286 }, "semantic": { "utterances": 6, "errors": 3, "words": 70, "wer": 0.04285714285714286 } }, "long": { "raw": { "utterances": 15, "errors": 2, "words": 412, "wer": 0.0048543689320388345 }, "semantic": { "utterances": 15, "errors": 2, "words": 432, "wer": 0.004629629629629629 } }, "long_range": { "raw": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 }, "semantic": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 } }, "names_places": { "raw": { "utterances": 6, "errors": 7, "words": 57, "wer": 0.12280701754385964 }, "semantic": { "utterances": 6, "errors": 7, "words": 57, "wer": 0.12280701754385964 } }, "narrative": { "raw": { "utterances": 24, "errors": 6, "words": 342, "wer": 0.017543859649122806 }, "semantic": { "utterances": 24, "errors": 6, "words": 352, "wer": 0.017045454545454544 } }, "numbers": { "raw": { "utterances": 6, "errors": 4, "words": 81, "wer": 0.04938271604938271 }, "semantic": { "utterances": 6, "errors": 5, "words": 64, "wer": 0.078125 } }, "punctuation": { "raw": { "utterances": 6, "errors": 2, "words": 65, "wer": 0.03076923076923077 }, "semantic": { "utterances": 6, "errors": 2, "words": 65, "wer": 0.03076923076923077 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 }, "semantic": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 } }, "short": { "raw": { "utterances": 24, "errors": 10, "words": 98, "wer": 0.10204081632653061 }, "semantic": { "utterances": 24, "errors": 10, "words": 105, "wer": 0.09523809523809523 } }, "technical": { "raw": { "utterances": 21, "errors": 8, "words": 251, "wer": 0.03187250996015936 }, "semantic": { "utterances": 21, "errors": 6, "words": 256, "wer": 0.0234375 } } } }, "whisper_large_v3": { "raw": { "utterances": 400, "errors": 146, "words": 6794, "wer": 0.021489549602590523 }, "raw_95ci": [ 0.015989811801330127, 0.02743585940975827 ], "semantic": { "utterances": 400, "errors": 148, "words": 6823, "wer": 0.021691338121061117 }, "semantic_95ci": [ 0.01564083997103548, 0.02847497431381183 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 1, "words": 296, "wer": 0.0033783783783783786 }, "semantic": { "utterances": 25, "errors": 1, "words": 309, "wer": 0.003236245954692557 } }, "descriptive": { "raw": { "utterances": 16, "errors": 1, "words": 217, "wer": 0.004608294930875576 }, "semantic": { "utterances": 16, "errors": 0, "words": 226, "wer": 0.0 } }, "emotional": { "raw": { "utterances": 24, "errors": 0, "words": 314, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 329, "wer": 0.0 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 89, "words": 4250, "wer": 0.020941176470588234 }, "semantic": { "utterances": 200, "errors": 123, "words": 4215, "wer": 0.029181494661921707 } }, "homographs": { "raw": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 }, "semantic": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 } }, "long": { "raw": { "utterances": 15, "errors": 1, "words": 412, "wer": 0.0024271844660194173 }, "semantic": { "utterances": 15, "errors": 1, "words": 432, "wer": 0.0023148148148148147 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 }, "semantic": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 } }, "narrative": { "raw": { "utterances": 24, "errors": 5, "words": 342, "wer": 0.014619883040935672 }, "semantic": { "utterances": 24, "errors": 4, "words": 352, "wer": 0.011363636363636364 } }, "numbers": { "raw": { "utterances": 6, "errors": 32, "words": 81, "wer": 0.3950617283950617 }, "semantic": { "utterances": 6, "errors": 6, "words": 64, "wer": 0.09375 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 }, "semantic": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 } }, "short": { "raw": { "utterances": 24, "errors": 2, "words": 98, "wer": 0.02040816326530612 }, "semantic": { "utterances": 24, "errors": 2, "words": 105, "wer": 0.01904761904761905 } }, "technical": { "raw": { "utterances": 21, "errors": 9, "words": 251, "wer": 0.035856573705179286 }, "semantic": { "utterances": 21, "errors": 5, "words": 256, "wer": 0.01953125 } } } }, "asr_macro_average": { "wer": 0.027602716302701644, "wer_95ci": [ 0.021376971841368126, 0.03446097015650821 ] } }, "kitten-nano-hugo": { "label": "KittenTTS Nano - Hugo", "qwen3_asr": { "raw": { "utterances": 400, "errors": 150, "words": 6794, "wer": 0.022078304386223137 }, "raw_95ci": [ 0.016605437178545186, 0.028407418310273772 ], "semantic": { "utterances": 400, "errors": 163, "words": 6823, "wer": 0.023889784552249743 }, "semantic_95ci": [ 0.0173235166738848, 0.03107674350744091 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 2, "words": 296, "wer": 0.006756756756756757 }, "semantic": { "utterances": 25, "errors": 2, "words": 309, "wer": 0.006472491909385114 } }, "descriptive": { "raw": { "utterances": 16, "errors": 3, "words": 217, "wer": 0.013824884792626729 }, "semantic": { "utterances": 16, "errors": 2, "words": 226, "wer": 0.008849557522123894 } }, "emotional": { "raw": { "utterances": 24, "errors": 0, "words": 314, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 329, "wer": 0.0 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 100, "words": 4250, "wer": 0.023529411764705882 }, "semantic": { "utterances": 200, "errors": 133, "words": 4215, "wer": 0.03155397390272835 } }, "homographs": { "raw": { "utterances": 6, "errors": 0, "words": 70, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 70, "wer": 0.0 } }, "long": { "raw": { "utterances": 15, "errors": 1, "words": 412, "wer": 0.0024271844660194173 }, "semantic": { "utterances": 15, "errors": 1, "words": 432, "wer": 0.0023148148148148147 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 7, "words": 57, "wer": 0.12280701754385964 }, "semantic": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 } }, "narrative": { "raw": { "utterances": 24, "errors": 4, "words": 342, "wer": 0.011695906432748537 }, "semantic": { "utterances": 24, "errors": 4, "words": 352, "wer": 0.011363636363636364 } }, "numbers": { "raw": { "utterances": 6, "errors": 20, "words": 81, "wer": 0.24691358024691357 }, "semantic": { "utterances": 6, "errors": 7, "words": 64, "wer": 0.109375 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 }, "semantic": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 } }, "short": { "raw": { "utterances": 24, "errors": 1, "words": 98, "wer": 0.01020408163265306 }, "semantic": { "utterances": 24, "errors": 1, "words": 105, "wer": 0.009523809523809525 } }, "technical": { "raw": { "utterances": 21, "errors": 9, "words": 251, "wer": 0.035856573705179286 }, "semantic": { "utterances": 21, "errors": 5, "words": 256, "wer": 0.01953125 } } } }, "nemotron35_asr": { "raw": { "utterances": 400, "errors": 287, "words": 6794, "wer": 0.04224315572564027 }, "raw_95ci": [ 0.034229828850855744, 0.05104311543810849 ], "semantic": { "utterances": 400, "errors": 259, "words": 6823, "wer": 0.037959841711856956 }, "semantic_95ci": [ 0.030281077948420748, 0.04660587639311044 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 3, "words": 296, "wer": 0.010135135135135136 }, "semantic": { "utterances": 25, "errors": 3, "words": 309, "wer": 0.009708737864077669 } }, "descriptive": { "raw": { "utterances": 16, "errors": 3, "words": 217, "wer": 0.013824884792626729 }, "semantic": { "utterances": 16, "errors": 3, "words": 226, "wer": 0.01327433628318584 } }, "emotional": { "raw": { "utterances": 24, "errors": 1, "words": 314, "wer": 0.0031847133757961785 }, "semantic": { "utterances": 24, "errors": 1, "words": 329, "wer": 0.00303951367781155 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 237, "words": 4250, "wer": 0.05576470588235294 }, "semantic": { "utterances": 200, "errors": 208, "words": 4215, "wer": 0.04934756820877817 } }, "homographs": { "raw": { "utterances": 6, "errors": 4, "words": 70, "wer": 0.05714285714285714 }, "semantic": { "utterances": 6, "errors": 4, "words": 70, "wer": 0.05714285714285714 } }, "long": { "raw": { "utterances": 15, "errors": 3, "words": 412, "wer": 0.007281553398058253 }, "semantic": { "utterances": 15, "errors": 3, "words": 432, "wer": 0.006944444444444444 } }, "long_range": { "raw": { "utterances": 6, "errors": 2, "words": 121, "wer": 0.01652892561983471 }, "semantic": { "utterances": 6, "errors": 2, "words": 121, "wer": 0.01652892561983471 } }, "names_places": { "raw": { "utterances": 6, "errors": 7, "words": 57, "wer": 0.12280701754385964 }, "semantic": { "utterances": 6, "errors": 7, "words": 57, "wer": 0.12280701754385964 } }, "narrative": { "raw": { "utterances": 24, "errors": 5, "words": 342, "wer": 0.014619883040935672 }, "semantic": { "utterances": 24, "errors": 5, "words": 352, "wer": 0.014204545454545454 } }, "numbers": { "raw": { "utterances": 6, "errors": 4, "words": 81, "wer": 0.04938271604938271 }, "semantic": { "utterances": 6, "errors": 6, "words": 64, "wer": 0.09375 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 }, "semantic": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 } }, "short": { "raw": { "utterances": 24, "errors": 6, "words": 98, "wer": 0.061224489795918366 }, "semantic": { "utterances": 24, "errors": 6, "words": 105, "wer": 0.05714285714285714 } }, "technical": { "raw": { "utterances": 21, "errors": 8, "words": 251, "wer": 0.03187250996015936 }, "semantic": { "utterances": 21, "errors": 7, "words": 256, "wer": 0.02734375 } } } }, "whisper_large_v3": { "raw": { "utterances": 400, "errors": 148, "words": 6794, "wer": 0.02178392699440683 }, "raw_95ci": [ 0.01613385121003884, 0.02785923753665689 ], "semantic": { "utterances": 400, "errors": 144, "words": 6823, "wer": 0.021105085739410816 }, "semantic_95ci": [ 0.015114082255486121, 0.027789966359514407 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 1, "words": 296, "wer": 0.0033783783783783786 }, "semantic": { "utterances": 25, "errors": 1, "words": 309, "wer": 0.003236245954692557 } }, "descriptive": { "raw": { "utterances": 16, "errors": 2, "words": 217, "wer": 0.009216589861751152 }, "semantic": { "utterances": 16, "errors": 1, "words": 226, "wer": 0.004424778761061947 } }, "emotional": { "raw": { "utterances": 24, "errors": 0, "words": 314, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 329, "wer": 0.0 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 89, "words": 4250, "wer": 0.020941176470588234 }, "semantic": { "utterances": 200, "errors": 116, "words": 4215, "wer": 0.02752075919335706 } }, "homographs": { "raw": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 }, "semantic": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 } }, "long": { "raw": { "utterances": 15, "errors": 1, "words": 412, "wer": 0.0024271844660194173 }, "semantic": { "utterances": 15, "errors": 1, "words": 432, "wer": 0.0023148148148148147 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 }, "semantic": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 } }, "narrative": { "raw": { "utterances": 24, "errors": 4, "words": 342, "wer": 0.011695906432748537 }, "semantic": { "utterances": 24, "errors": 3, "words": 352, "wer": 0.008522727272727272 } }, "numbers": { "raw": { "utterances": 6, "errors": 32, "words": 81, "wer": 0.3950617283950617 }, "semantic": { "utterances": 6, "errors": 8, "words": 64, "wer": 0.125 } }, "punctuation": { "raw": { "utterances": 6, "errors": 1, "words": 65, "wer": 0.015384615384615385 }, "semantic": { "utterances": 6, "errors": 1, "words": 65, "wer": 0.015384615384615385 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 }, "semantic": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 } }, "short": { "raw": { "utterances": 24, "errors": 2, "words": 98, "wer": 0.02040816326530612 }, "semantic": { "utterances": 24, "errors": 2, "words": 105, "wer": 0.01904761904761905 } }, "technical": { "raw": { "utterances": 21, "errors": 10, "words": 251, "wer": 0.0398406374501992 }, "semantic": { "utterances": 21, "errors": 6, "words": 256, "wer": 0.0234375 } } } }, "asr_macro_average": { "wer": 0.027651570667839173, "wer_95ci": [ 0.021452384403536747, 0.0344283318536056 ] } }, "piper-ryan-low": { "label": "Piper - Ryan Low", "qwen3_asr": { "raw": { "utterances": 400, "errors": 181, "words": 6794, "wer": 0.02664115395937592 }, "raw_95ci": [ 0.02094850160023276, 0.03278688524590164 ], "semantic": { "utterances": 400, "errors": 192, "words": 6823, "wer": 0.028140114319214423 }, "semantic_95ci": [ 0.021386536529352664, 0.03574504737295435 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 2, "words": 296, "wer": 0.006756756756756757 }, "semantic": { "utterances": 25, "errors": 2, "words": 309, "wer": 0.006472491909385114 } }, "descriptive": { "raw": { "utterances": 16, "errors": 0, "words": 217, "wer": 0.0 }, "semantic": { "utterances": 16, "errors": 0, "words": 226, "wer": 0.0 } }, "emotional": { "raw": { "utterances": 24, "errors": 0, "words": 314, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 329, "wer": 0.0 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 130, "words": 4250, "wer": 0.03058823529411765 }, "semantic": { "utterances": 200, "errors": 153, "words": 4215, "wer": 0.036298932384341634 } }, "homographs": { "raw": { "utterances": 6, "errors": 3, "words": 70, "wer": 0.04285714285714286 }, "semantic": { "utterances": 6, "errors": 3, "words": 70, "wer": 0.04285714285714286 } }, "long": { "raw": { "utterances": 15, "errors": 3, "words": 412, "wer": 0.007281553398058253 }, "semantic": { "utterances": 15, "errors": 3, "words": 432, "wer": 0.006944444444444444 } }, "long_range": { "raw": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 }, "semantic": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 } }, "names_places": { "raw": { "utterances": 6, "errors": 14, "words": 57, "wer": 0.24561403508771928 }, "semantic": { "utterances": 6, "errors": 14, "words": 57, "wer": 0.24561403508771928 } }, "narrative": { "raw": { "utterances": 24, "errors": 1, "words": 342, "wer": 0.0029239766081871343 }, "semantic": { "utterances": 24, "errors": 1, "words": 352, "wer": 0.002840909090909091 } }, "numbers": { "raw": { "utterances": 6, "errors": 11, "words": 81, "wer": 0.13580246913580246 }, "semantic": { "utterances": 6, "errors": 3, "words": 64, "wer": 0.046875 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 }, "semantic": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 } }, "short": { "raw": { "utterances": 24, "errors": 3, "words": 98, "wer": 0.030612244897959183 }, "semantic": { "utterances": 24, "errors": 3, "words": 105, "wer": 0.02857142857142857 } }, "technical": { "raw": { "utterances": 21, "errors": 9, "words": 251, "wer": 0.035856573705179286 }, "semantic": { "utterances": 21, "errors": 5, "words": 256, "wer": 0.01953125 } } } }, "nemotron35_asr": { "raw": { "utterances": 400, "errors": 442, "words": 6794, "wer": 0.06505740359140418 }, "raw_95ci": [ 0.054938545831482305, 0.07616320687186828 ], "semantic": { "utterances": 400, "errors": 376, "words": 6823, "wer": 0.055107723875128245 }, "semantic_95ci": [ 0.04650152107779226, 0.06445341707791237 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 10, "words": 296, "wer": 0.033783783783783786 }, "semantic": { "utterances": 25, "errors": 8, "words": 309, "wer": 0.025889967637540454 } }, "descriptive": { "raw": { "utterances": 16, "errors": 7, "words": 217, "wer": 0.03225806451612903 }, "semantic": { "utterances": 16, "errors": 7, "words": 226, "wer": 0.030973451327433628 } }, "emotional": { "raw": { "utterances": 24, "errors": 1, "words": 314, "wer": 0.0031847133757961785 }, "semantic": { "utterances": 24, "errors": 1, "words": 329, "wer": 0.00303951367781155 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 347, "words": 4250, "wer": 0.0816470588235294 }, "semantic": { "utterances": 200, "errors": 284, "words": 4215, "wer": 0.06737841043890866 } }, "homographs": { "raw": { "utterances": 6, "errors": 7, "words": 70, "wer": 0.1 }, "semantic": { "utterances": 6, "errors": 7, "words": 70, "wer": 0.1 } }, "long": { "raw": { "utterances": 15, "errors": 9, "words": 412, "wer": 0.021844660194174758 }, "semantic": { "utterances": 15, "errors": 9, "words": 432, "wer": 0.020833333333333332 } }, "long_range": { "raw": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 }, "semantic": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 } }, "names_places": { "raw": { "utterances": 6, "errors": 24, "words": 57, "wer": 0.42105263157894735 }, "semantic": { "utterances": 6, "errors": 24, "words": 57, "wer": 0.42105263157894735 } }, "narrative": { "raw": { "utterances": 24, "errors": 4, "words": 342, "wer": 0.011695906432748537 }, "semantic": { "utterances": 24, "errors": 4, "words": 352, "wer": 0.011363636363636364 } }, "numbers": { "raw": { "utterances": 6, "errors": 5, "words": 81, "wer": 0.06172839506172839 }, "semantic": { "utterances": 6, "errors": 5, "words": 64, "wer": 0.078125 } }, "punctuation": { "raw": { "utterances": 6, "errors": 1, "words": 65, "wer": 0.015384615384615385 }, "semantic": { "utterances": 6, "errors": 1, "words": 65, "wer": 0.015384615384615385 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 }, "semantic": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 } }, "short": { "raw": { "utterances": 24, "errors": 10, "words": 98, "wer": 0.10204081632653061 }, "semantic": { "utterances": 24, "errors": 10, "words": 105, "wer": 0.09523809523809523 } }, "technical": { "raw": { "utterances": 21, "errors": 10, "words": 251, "wer": 0.0398406374501992 }, "semantic": { "utterances": 21, "errors": 9, "words": 256, "wer": 0.03515625 } } } }, "whisper_large_v3": { "raw": { "utterances": 400, "errors": 192, "words": 6794, "wer": 0.028260229614365615 }, "raw_95ci": [ 0.02239140170174653, 0.034622911335240106 ], "semantic": { "utterances": 400, "errors": 196, "words": 6823, "wer": 0.028726366700864724 }, "semantic_95ci": [ 0.0221175799086758, 0.03601981089599279 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 8, "words": 296, "wer": 0.02702702702702703 }, "semantic": { "utterances": 25, "errors": 5, "words": 309, "wer": 0.016181229773462782 } }, "descriptive": { "raw": { "utterances": 16, "errors": 3, "words": 217, "wer": 0.013824884792626729 }, "semantic": { "utterances": 16, "errors": 1, "words": 226, "wer": 0.004424778761061947 } }, "emotional": { "raw": { "utterances": 24, "errors": 1, "words": 314, "wer": 0.0031847133757961785 }, "semantic": { "utterances": 24, "errors": 1, "words": 329, "wer": 0.00303951367781155 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 118, "words": 4250, "wer": 0.02776470588235294 }, "semantic": { "utterances": 200, "errors": 157, "words": 4215, "wer": 0.037247924080664296 } }, "homographs": { "raw": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 }, "semantic": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 } }, "long": { "raw": { "utterances": 15, "errors": 3, "words": 412, "wer": 0.007281553398058253 }, "semantic": { "utterances": 15, "errors": 3, "words": 432, "wer": 0.006944444444444444 } }, "long_range": { "raw": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 }, "semantic": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 } }, "names_places": { "raw": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 }, "semantic": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 } }, "narrative": { "raw": { "utterances": 24, "errors": 1, "words": 342, "wer": 0.0029239766081871343 }, "semantic": { "utterances": 24, "errors": 0, "words": 352, "wer": 0.0 } }, "numbers": { "raw": { "utterances": 6, "errors": 32, "words": 81, "wer": 0.3950617283950617 }, "semantic": { "utterances": 6, "errors": 6, "words": 64, "wer": 0.09375 } }, "punctuation": { "raw": { "utterances": 6, "errors": 1, "words": 65, "wer": 0.015384615384615385 }, "semantic": { "utterances": 6, "errors": 1, "words": 65, "wer": 0.015384615384615385 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 }, "semantic": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 } }, "short": { "raw": { "utterances": 24, "errors": 7, "words": 98, "wer": 0.07142857142857142 }, "semantic": { "utterances": 24, "errors": 8, "words": 105, "wer": 0.0761904761904762 } }, "technical": { "raw": { "utterances": 21, "errors": 10, "words": 251, "wer": 0.0398406374501992 }, "semantic": { "utterances": 21, "errors": 6, "words": 256, "wer": 0.0234375 } } } }, "asr_macro_average": { "wer": 0.03732473496506913, "wer_95ci": [ 0.030795019157088124, 0.04458376872169976 ] } }, "piper-danny-low": { "label": "Piper - Danny Low", "qwen3_asr": { "raw": { "utterances": 400, "errors": 175, "words": 6794, "wer": 0.025758021783926995 }, "raw_95ci": [ 0.01956489998539933, 0.03292759051186017 ], "semantic": { "utterances": 400, "errors": 179, "words": 6823, "wer": 0.026234794078850945 }, "semantic_95ci": [ 0.019979876383498633, 0.03340659340659341 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 2, "words": 296, "wer": 0.006756756756756757 }, "semantic": { "utterances": 25, "errors": 2, "words": 309, "wer": 0.006472491909385114 } }, "descriptive": { "raw": { "utterances": 16, "errors": 2, "words": 217, "wer": 0.009216589861751152 }, "semantic": { "utterances": 16, "errors": 2, "words": 226, "wer": 0.008849557522123894 } }, "emotional": { "raw": { "utterances": 24, "errors": 1, "words": 314, "wer": 0.0031847133757961785 }, "semantic": { "utterances": 24, "errors": 1, "words": 329, "wer": 0.00303951367781155 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 131, "words": 4250, "wer": 0.030823529411764704 }, "semantic": { "utterances": 200, "errors": 150, "words": 4215, "wer": 0.03558718861209965 } }, "homographs": { "raw": { "utterances": 6, "errors": 0, "words": 70, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 70, "wer": 0.0 } }, "long": { "raw": { "utterances": 15, "errors": 5, "words": 412, "wer": 0.012135922330097087 }, "semantic": { "utterances": 15, "errors": 5, "words": 432, "wer": 0.011574074074074073 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 }, "semantic": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 } }, "narrative": { "raw": { "utterances": 24, "errors": 0, "words": 342, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 352, "wer": 0.0 } }, "numbers": { "raw": { "utterances": 6, "errors": 13, "words": 81, "wer": 0.16049382716049382 }, "semantic": { "utterances": 6, "errors": 2, "words": 64, "wer": 0.03125 } }, "punctuation": { "raw": { "utterances": 6, "errors": 1, "words": 65, "wer": 0.015384615384615385 }, "semantic": { "utterances": 6, "errors": 1, "words": 65, "wer": 0.015384615384615385 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 }, "semantic": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 } }, "short": { "raw": { "utterances": 24, "errors": 2, "words": 98, "wer": 0.02040816326530612 }, "semantic": { "utterances": 24, "errors": 2, "words": 105, "wer": 0.01904761904761905 } }, "technical": { "raw": { "utterances": 21, "errors": 9, "words": 251, "wer": 0.035856573705179286 }, "semantic": { "utterances": 21, "errors": 5, "words": 256, "wer": 0.01953125 } } } }, "nemotron35_asr": { "raw": { "utterances": 400, "errors": 438, "words": 6794, "wer": 0.06446864880777156 }, "raw_95ci": [ 0.05425912670007158, 0.07542874487782668 ], "semantic": { "utterances": 400, "errors": 382, "words": 6823, "wer": 0.055987102447603694 }, "semantic_95ci": [ 0.04722822174226062, 0.06521079769487413 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 4, "words": 296, "wer": 0.013513513513513514 }, "semantic": { "utterances": 25, "errors": 4, "words": 309, "wer": 0.012944983818770227 } }, "descriptive": { "raw": { "utterances": 16, "errors": 4, "words": 217, "wer": 0.018433179723502304 }, "semantic": { "utterances": 16, "errors": 4, "words": 226, "wer": 0.017699115044247787 } }, "emotional": { "raw": { "utterances": 24, "errors": 3, "words": 314, "wer": 0.009554140127388535 }, "semantic": { "utterances": 24, "errors": 3, "words": 329, "wer": 0.00911854103343465 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 349, "words": 4250, "wer": 0.08211764705882353 }, "semantic": { "utterances": 200, "errors": 295, "words": 4215, "wer": 0.06998813760379596 } }, "homographs": { "raw": { "utterances": 6, "errors": 3, "words": 70, "wer": 0.04285714285714286 }, "semantic": { "utterances": 6, "errors": 3, "words": 70, "wer": 0.04285714285714286 } }, "long": { "raw": { "utterances": 15, "errors": 19, "words": 412, "wer": 0.04611650485436893 }, "semantic": { "utterances": 15, "errors": 19, "words": 432, "wer": 0.04398148148148148 } }, "long_range": { "raw": { "utterances": 6, "errors": 4, "words": 121, "wer": 0.03305785123966942 }, "semantic": { "utterances": 6, "errors": 4, "words": 121, "wer": 0.03305785123966942 } }, "names_places": { "raw": { "utterances": 6, "errors": 13, "words": 57, "wer": 0.22807017543859648 }, "semantic": { "utterances": 6, "errors": 13, "words": 57, "wer": 0.22807017543859648 } }, "narrative": { "raw": { "utterances": 24, "errors": 1, "words": 342, "wer": 0.0029239766081871343 }, "semantic": { "utterances": 24, "errors": 1, "words": 352, "wer": 0.002840909090909091 } }, "numbers": { "raw": { "utterances": 6, "errors": 5, "words": 81, "wer": 0.06172839506172839 }, "semantic": { "utterances": 6, "errors": 4, "words": 64, "wer": 0.0625 } }, "punctuation": { "raw": { "utterances": 6, "errors": 1, "words": 65, "wer": 0.015384615384615385 }, "semantic": { "utterances": 6, "errors": 1, "words": 65, "wer": 0.015384615384615385 } }, "question": { "raw": { "utterances": 15, "errors": 1, "words": 163, "wer": 0.006134969325153374 }, "semantic": { "utterances": 15, "errors": 1, "words": 165, "wer": 0.006060606060606061 } }, "rare_words": { "raw": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 }, "semantic": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 } }, "short": { "raw": { "utterances": 24, "errors": 3, "words": 98, "wer": 0.030612244897959183 }, "semantic": { "utterances": 24, "errors": 3, "words": 105, "wer": 0.02857142857142857 } }, "technical": { "raw": { "utterances": 21, "errors": 24, "words": 251, "wer": 0.09561752988047809 }, "semantic": { "utterances": 21, "errors": 23, "words": 256, "wer": 0.08984375 } } } }, "whisper_large_v3": { "raw": { "utterances": 400, "errors": 166, "words": 6794, "wer": 0.024433323520753607 }, "raw_95ci": [ 0.018651148910772904, 0.030638170677028845 ], "semantic": { "utterances": 400, "errors": 174, "words": 6823, "wer": 0.02550197860178807 }, "semantic_95ci": [ 0.019211324570273004, 0.03259413603214764 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 2, "words": 296, "wer": 0.006756756756756757 }, "semantic": { "utterances": 25, "errors": 2, "words": 309, "wer": 0.006472491909385114 } }, "descriptive": { "raw": { "utterances": 16, "errors": 2, "words": 217, "wer": 0.009216589861751152 }, "semantic": { "utterances": 16, "errors": 1, "words": 226, "wer": 0.004424778761061947 } }, "emotional": { "raw": { "utterances": 24, "errors": 1, "words": 314, "wer": 0.0031847133757961785 }, "semantic": { "utterances": 24, "errors": 1, "words": 329, "wer": 0.00303951367781155 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 100, "words": 4250, "wer": 0.023529411764705882 }, "semantic": { "utterances": 200, "errors": 140, "words": 4215, "wer": 0.033214709371293 } }, "homographs": { "raw": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 }, "semantic": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 } }, "long": { "raw": { "utterances": 15, "errors": 7, "words": 412, "wer": 0.01699029126213592 }, "semantic": { "utterances": 15, "errors": 7, "words": 432, "wer": 0.016203703703703703 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 }, "semantic": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 } }, "narrative": { "raw": { "utterances": 24, "errors": 1, "words": 342, "wer": 0.0029239766081871343 }, "semantic": { "utterances": 24, "errors": 0, "words": 352, "wer": 0.0 } }, "numbers": { "raw": { "utterances": 6, "errors": 33, "words": 81, "wer": 0.4074074074074074 }, "semantic": { "utterances": 6, "errors": 7, "words": 64, "wer": 0.109375 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 2, "words": 163, "wer": 0.012269938650306749 }, "semantic": { "utterances": 15, "errors": 2, "words": 165, "wer": 0.012121212121212121 } }, "rare_words": { "raw": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 }, "semantic": { "utterances": 6, "errors": 2, "words": 57, "wer": 0.03508771929824561 } }, "short": { "raw": { "utterances": 24, "errors": 3, "words": 98, "wer": 0.030612244897959183 }, "semantic": { "utterances": 24, "errors": 3, "words": 105, "wer": 0.02857142857142857 } }, "technical": { "raw": { "utterances": 21, "errors": 9, "words": 251, "wer": 0.035856573705179286 }, "semantic": { "utterances": 21, "errors": 5, "words": 256, "wer": 0.01953125 } } } }, "asr_macro_average": { "wer": 0.0359079583760809, "wer_95ci": [ 0.029313597445943983, 0.04306619524651345 ] } }, "supertonic3-m2-3step": { "label": "Supertonic 3 - M2 - 3-step", "qwen3_asr": { "raw": { "utterances": 400, "errors": 200, "words": 6794, "wer": 0.02943773918163085 }, "raw_95ci": [ 0.023245740687265377, 0.03628800917957545 ], "semantic": { "utterances": 400, "errors": 207, "words": 6823, "wer": 0.03033856075040305 }, "semantic_95ci": [ 0.02375875723423698, 0.03767123287671233 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 0, "words": 296, "wer": 0.0 }, "semantic": { "utterances": 25, "errors": 0, "words": 309, "wer": 0.0 } }, "descriptive": { "raw": { "utterances": 16, "errors": 1, "words": 217, "wer": 0.004608294930875576 }, "semantic": { "utterances": 16, "errors": 1, "words": 226, "wer": 0.004424778761061947 } }, "emotional": { "raw": { "utterances": 24, "errors": 1, "words": 314, "wer": 0.0031847133757961785 }, "semantic": { "utterances": 24, "errors": 1, "words": 329, "wer": 0.00303951367781155 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 120, "words": 4250, "wer": 0.02823529411764706 }, "semantic": { "utterances": 200, "errors": 153, "words": 4215, "wer": 0.036298932384341634 } }, "homographs": { "raw": { "utterances": 6, "errors": 4, "words": 70, "wer": 0.05714285714285714 }, "semantic": { "utterances": 6, "errors": 4, "words": 70, "wer": 0.05714285714285714 } }, "long": { "raw": { "utterances": 15, "errors": 6, "words": 412, "wer": 0.014563106796116505 }, "semantic": { "utterances": 15, "errors": 6, "words": 432, "wer": 0.013888888888888888 } }, "long_range": { "raw": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 }, "semantic": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 } }, "names_places": { "raw": { "utterances": 6, "errors": 10, "words": 57, "wer": 0.17543859649122806 }, "semantic": { "utterances": 6, "errors": 10, "words": 57, "wer": 0.17543859649122806 } }, "narrative": { "raw": { "utterances": 24, "errors": 0, "words": 342, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 352, "wer": 0.0 } }, "numbers": { "raw": { "utterances": 6, "errors": 24, "words": 81, "wer": 0.2962962962962963 }, "semantic": { "utterances": 6, "errors": 2, "words": 64, "wer": 0.03125 } }, "punctuation": { "raw": { "utterances": 6, "errors": 3, "words": 65, "wer": 0.046153846153846156 }, "semantic": { "utterances": 6, "errors": 3, "words": 65, "wer": 0.046153846153846156 } }, "question": { "raw": { "utterances": 15, "errors": 1, "words": 163, "wer": 0.006134969325153374 }, "semantic": { "utterances": 15, "errors": 1, "words": 165, "wer": 0.006060606060606061 } }, "rare_words": { "raw": { "utterances": 6, "errors": 7, "words": 57, "wer": 0.12280701754385964 }, "semantic": { "utterances": 6, "errors": 7, "words": 57, "wer": 0.12280701754385964 } }, "short": { "raw": { "utterances": 24, "errors": 13, "words": 98, "wer": 0.1326530612244898 }, "semantic": { "utterances": 24, "errors": 13, "words": 105, "wer": 0.12380952380952381 } }, "technical": { "raw": { "utterances": 21, "errors": 9, "words": 251, "wer": 0.035856573705179286 }, "semantic": { "utterances": 21, "errors": 5, "words": 256, "wer": 0.01953125 } } } }, "nemotron35_asr": { "raw": { "utterances": 400, "errors": 446, "words": 6794, "wer": 0.0656461583750368 }, "raw_95ci": [ 0.05547445255474453, 0.07639304973037747 ], "semantic": { "utterances": 400, "errors": 412, "words": 6823, "wer": 0.060383995309980946 }, "semantic_95ci": [ 0.05129658495111237, 0.07025560474082536 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 7, "words": 296, "wer": 0.02364864864864865 }, "semantic": { "utterances": 25, "errors": 7, "words": 309, "wer": 0.022653721682847898 } }, "descriptive": { "raw": { "utterances": 16, "errors": 1, "words": 217, "wer": 0.004608294930875576 }, "semantic": { "utterances": 16, "errors": 1, "words": 226, "wer": 0.004424778761061947 } }, "emotional": { "raw": { "utterances": 24, "errors": 7, "words": 314, "wer": 0.022292993630573247 }, "semantic": { "utterances": 24, "errors": 7, "words": 329, "wer": 0.02127659574468085 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 324, "words": 4250, "wer": 0.07623529411764705 }, "semantic": { "utterances": 200, "errors": 292, "words": 4215, "wer": 0.06927639383155397 } }, "homographs": { "raw": { "utterances": 6, "errors": 7, "words": 70, "wer": 0.1 }, "semantic": { "utterances": 6, "errors": 7, "words": 70, "wer": 0.1 } }, "long": { "raw": { "utterances": 15, "errors": 9, "words": 412, "wer": 0.021844660194174758 }, "semantic": { "utterances": 15, "errors": 7, "words": 432, "wer": 0.016203703703703703 } }, "long_range": { "raw": { "utterances": 6, "errors": 4, "words": 121, "wer": 0.03305785123966942 }, "semantic": { "utterances": 6, "errors": 4, "words": 121, "wer": 0.03305785123966942 } }, "names_places": { "raw": { "utterances": 6, "errors": 12, "words": 57, "wer": 0.21052631578947367 }, "semantic": { "utterances": 6, "errors": 12, "words": 57, "wer": 0.21052631578947367 } }, "narrative": { "raw": { "utterances": 24, "errors": 1, "words": 342, "wer": 0.0029239766081871343 }, "semantic": { "utterances": 24, "errors": 1, "words": 352, "wer": 0.002840909090909091 } }, "numbers": { "raw": { "utterances": 6, "errors": 4, "words": 81, "wer": 0.04938271604938271 }, "semantic": { "utterances": 6, "errors": 3, "words": 64, "wer": 0.046875 } }, "punctuation": { "raw": { "utterances": 6, "errors": 8, "words": 65, "wer": 0.12307692307692308 }, "semantic": { "utterances": 6, "errors": 9, "words": 65, "wer": 0.13846153846153847 } }, "question": { "raw": { "utterances": 15, "errors": 9, "words": 163, "wer": 0.05521472392638037 }, "semantic": { "utterances": 15, "errors": 9, "words": 165, "wer": 0.05454545454545454 } }, "rare_words": { "raw": { "utterances": 6, "errors": 10, "words": 57, "wer": 0.17543859649122806 }, "semantic": { "utterances": 6, "errors": 10, "words": 57, "wer": 0.17543859649122806 } }, "short": { "raw": { "utterances": 24, "errors": 31, "words": 98, "wer": 0.3163265306122449 }, "semantic": { "utterances": 24, "errors": 31, "words": 105, "wer": 0.29523809523809524 } }, "technical": { "raw": { "utterances": 21, "errors": 12, "words": 251, "wer": 0.04780876494023904 }, "semantic": { "utterances": 21, "errors": 12, "words": 256, "wer": 0.046875 } } } }, "whisper_large_v3": { "raw": { "utterances": 400, "errors": 221, "words": 6794, "wer": 0.03252870179570209 }, "raw_95ci": [ 0.025667502581501696, 0.04004781829049611 ], "semantic": { "utterances": 400, "errors": 220, "words": 6823, "wer": 0.03224388099076653 }, "semantic_95ci": [ 0.02492877492877493, 0.04039812646370024 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 1, "words": 296, "wer": 0.0033783783783783786 }, "semantic": { "utterances": 25, "errors": 1, "words": 309, "wer": 0.003236245954692557 } }, "descriptive": { "raw": { "utterances": 16, "errors": 2, "words": 217, "wer": 0.009216589861751152 }, "semantic": { "utterances": 16, "errors": 1, "words": 226, "wer": 0.004424778761061947 } }, "emotional": { "raw": { "utterances": 24, "errors": 2, "words": 314, "wer": 0.006369426751592357 }, "semantic": { "utterances": 24, "errors": 2, "words": 329, "wer": 0.0060790273556231 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 132, "words": 4250, "wer": 0.031058823529411764 }, "semantic": { "utterances": 200, "errors": 162, "words": 4215, "wer": 0.038434163701067614 } }, "homographs": { "raw": { "utterances": 6, "errors": 2, "words": 70, "wer": 0.02857142857142857 }, "semantic": { "utterances": 6, "errors": 2, "words": 70, "wer": 0.02857142857142857 } }, "long": { "raw": { "utterances": 15, "errors": 4, "words": 412, "wer": 0.009708737864077669 }, "semantic": { "utterances": 15, "errors": 4, "words": 432, "wer": 0.009259259259259259 } }, "long_range": { "raw": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 }, "semantic": { "utterances": 6, "errors": 1, "words": 121, "wer": 0.008264462809917356 } }, "names_places": { "raw": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 }, "semantic": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 } }, "narrative": { "raw": { "utterances": 24, "errors": 1, "words": 342, "wer": 0.0029239766081871343 }, "semantic": { "utterances": 24, "errors": 0, "words": 352, "wer": 0.0 } }, "numbers": { "raw": { "utterances": 6, "errors": 32, "words": 81, "wer": 0.3950617283950617 }, "semantic": { "utterances": 6, "errors": 5, "words": 64, "wer": 0.078125 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 7, "words": 163, "wer": 0.04294478527607362 }, "semantic": { "utterances": 15, "errors": 8, "words": 165, "wer": 0.048484848484848485 } }, "rare_words": { "raw": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 }, "semantic": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 } }, "short": { "raw": { "utterances": 24, "errors": 17, "words": 98, "wer": 0.17346938775510204 }, "semantic": { "utterances": 24, "errors": 18, "words": 105, "wer": 0.17142857142857143 } }, "technical": { "raw": { "utterances": 21, "errors": 10, "words": 251, "wer": 0.0398406374501992 }, "semantic": { "utterances": 21, "errors": 6, "words": 256, "wer": 0.0234375 } } } }, "asr_macro_average": { "wer": 0.040988812350383506, "wer_95ci": [ 0.034040477932211655, 0.04855302374771656 ] } }, "supertonic3-m2-8step": { "label": "Supertonic 3 - M2 - 8-step", "qwen3_asr": { "raw": { "utterances": 400, "errors": 137, "words": 6794, "wer": 0.020164851339417134 }, "raw_95ci": [ 0.014720886168197056, 0.026397286535909156 ], "semantic": { "utterances": 400, "errors": 140, "words": 6823, "wer": 0.020518833357760516 }, "semantic_95ci": [ 0.014671013633669235, 0.02735562310030395 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 0, "words": 296, "wer": 0.0 }, "semantic": { "utterances": 25, "errors": 0, "words": 309, "wer": 0.0 } }, "descriptive": { "raw": { "utterances": 16, "errors": 1, "words": 217, "wer": 0.004608294930875576 }, "semantic": { "utterances": 16, "errors": 0, "words": 226, "wer": 0.0 } }, "emotional": { "raw": { "utterances": 24, "errors": 1, "words": 314, "wer": 0.0031847133757961785 }, "semantic": { "utterances": 24, "errors": 1, "words": 329, "wer": 0.00303951367781155 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 89, "words": 4250, "wer": 0.020941176470588234 }, "semantic": { "utterances": 200, "errors": 119, "words": 4215, "wer": 0.02823250296559905 } }, "homographs": { "raw": { "utterances": 6, "errors": 0, "words": 70, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 70, "wer": 0.0 } }, "long": { "raw": { "utterances": 15, "errors": 3, "words": 412, "wer": 0.007281553398058253 }, "semantic": { "utterances": 15, "errors": 3, "words": 432, "wer": 0.006944444444444444 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 }, "semantic": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 } }, "narrative": { "raw": { "utterances": 24, "errors": 0, "words": 342, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 352, "wer": 0.0 } }, "numbers": { "raw": { "utterances": 6, "errors": 24, "words": 81, "wer": 0.2962962962962963 }, "semantic": { "utterances": 6, "errors": 2, "words": 64, "wer": 0.03125 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 }, "semantic": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 } }, "short": { "raw": { "utterances": 24, "errors": 1, "words": 98, "wer": 0.01020408163265306 }, "semantic": { "utterances": 24, "errors": 1, "words": 105, "wer": 0.009523809523809525 } }, "technical": { "raw": { "utterances": 21, "errors": 9, "words": 251, "wer": 0.035856573705179286 }, "semantic": { "utterances": 21, "errors": 5, "words": 256, "wer": 0.01953125 } } } }, "nemotron35_asr": { "raw": { "utterances": 400, "errors": 284, "words": 6794, "wer": 0.04180158963791581 }, "raw_95ci": [ 0.033854950346072825, 0.050436615477265884 ], "semantic": { "utterances": 400, "errors": 243, "words": 6823, "wer": 0.035614832185255754 }, "semantic_95ci": [ 0.028567347521782603, 0.043412264723740136 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 1, "words": 296, "wer": 0.0033783783783783786 }, "semantic": { "utterances": 25, "errors": 1, "words": 309, "wer": 0.003236245954692557 } }, "descriptive": { "raw": { "utterances": 16, "errors": 3, "words": 217, "wer": 0.013824884792626729 }, "semantic": { "utterances": 16, "errors": 3, "words": 226, "wer": 0.01327433628318584 } }, "emotional": { "raw": { "utterances": 24, "errors": 1, "words": 314, "wer": 0.0031847133757961785 }, "semantic": { "utterances": 24, "errors": 1, "words": 329, "wer": 0.00303951367781155 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 245, "words": 4250, "wer": 0.05764705882352941 }, "semantic": { "utterances": 200, "errors": 205, "words": 4215, "wer": 0.04863582443653618 } }, "homographs": { "raw": { "utterances": 6, "errors": 2, "words": 70, "wer": 0.02857142857142857 }, "semantic": { "utterances": 6, "errors": 2, "words": 70, "wer": 0.02857142857142857 } }, "long": { "raw": { "utterances": 15, "errors": 4, "words": 412, "wer": 0.009708737864077669 }, "semantic": { "utterances": 15, "errors": 4, "words": 432, "wer": 0.009259259259259259 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 11, "words": 57, "wer": 0.19298245614035087 }, "semantic": { "utterances": 6, "errors": 11, "words": 57, "wer": 0.19298245614035087 } }, "narrative": { "raw": { "utterances": 24, "errors": 0, "words": 342, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 352, "wer": 0.0 } }, "numbers": { "raw": { "utterances": 6, "errors": 3, "words": 81, "wer": 0.037037037037037035 }, "semantic": { "utterances": 6, "errors": 2, "words": 64, "wer": 0.03125 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 }, "semantic": { "utterances": 6, "errors": 5, "words": 57, "wer": 0.08771929824561403 } }, "short": { "raw": { "utterances": 24, "errors": 3, "words": 98, "wer": 0.030612244897959183 }, "semantic": { "utterances": 24, "errors": 3, "words": 105, "wer": 0.02857142857142857 } }, "technical": { "raw": { "utterances": 21, "errors": 6, "words": 251, "wer": 0.02390438247011952 }, "semantic": { "utterances": 21, "errors": 6, "words": 256, "wer": 0.0234375 } } } }, "whisper_large_v3": { "raw": { "utterances": 400, "errors": 552, "words": 6794, "wer": 0.08124816014130115 }, "raw_95ci": [ 0.017957850994360345, 0.20512431776834444 ], "semantic": { "utterances": 400, "errors": 551, "words": 6823, "wer": 0.08075626557232889 }, "semantic_95ci": [ 0.0176792479304055, 0.20577239419769702 ], "categories": { "conversational": { "raw": { "utterances": 25, "errors": 400, "words": 296, "wer": 1.3513513513513513 }, "semantic": { "utterances": 25, "errors": 400, "words": 309, "wer": 1.2944983818770226 } }, "descriptive": { "raw": { "utterances": 16, "errors": 1, "words": 217, "wer": 0.004608294930875576 }, "semantic": { "utterances": 16, "errors": 0, "words": 226, "wer": 0.0 } }, "emotional": { "raw": { "utterances": 24, "errors": 0, "words": 314, "wer": 0.0 }, "semantic": { "utterances": 24, "errors": 0, "words": 329, "wer": 0.0 } }, "external_heldout": { "raw": { "utterances": 200, "errors": 93, "words": 4250, "wer": 0.02188235294117647 }, "semantic": { "utterances": 200, "errors": 125, "words": 4215, "wer": 0.02965599051008304 } }, "homographs": { "raw": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 }, "semantic": { "utterances": 6, "errors": 1, "words": 70, "wer": 0.014285714285714285 } }, "long": { "raw": { "utterances": 15, "errors": 3, "words": 412, "wer": 0.007281553398058253 }, "semantic": { "utterances": 15, "errors": 3, "words": 432, "wer": 0.006944444444444444 } }, "long_range": { "raw": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 121, "wer": 0.0 } }, "names_places": { "raw": { "utterances": 6, "errors": 4, "words": 57, "wer": 0.07017543859649122 }, "semantic": { "utterances": 6, "errors": 3, "words": 57, "wer": 0.05263157894736842 } }, "narrative": { "raw": { "utterances": 24, "errors": 1, "words": 342, "wer": 0.0029239766081871343 }, "semantic": { "utterances": 24, "errors": 0, "words": 352, "wer": 0.0 } }, "numbers": { "raw": { "utterances": 6, "errors": 32, "words": 81, "wer": 0.3950617283950617 }, "semantic": { "utterances": 6, "errors": 6, "words": 64, "wer": 0.09375 } }, "punctuation": { "raw": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 }, "semantic": { "utterances": 6, "errors": 0, "words": 65, "wer": 0.0 } }, "question": { "raw": { "utterances": 15, "errors": 0, "words": 163, "wer": 0.0 }, "semantic": { "utterances": 15, "errors": 0, "words": 165, "wer": 0.0 } }, "rare_words": { "raw": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 }, "semantic": { "utterances": 6, "errors": 6, "words": 57, "wer": 0.10526315789473684 } }, "short": { "raw": { "utterances": 24, "errors": 1, "words": 98, "wer": 0.01020408163265306 }, "semantic": { "utterances": 24, "errors": 1, "words": 105, "wer": 0.009523809523809525 } }, "technical": { "raw": { "utterances": 21, "errors": 10, "words": 251, "wer": 0.0398406374501992 }, "semantic": { "utterances": 21, "errors": 6, "words": 256, "wer": 0.0234375 } } } }, "asr_macro_average": { "wer": 0.04562997703844838, "wer_95ci": [ 0.021539744302390213, 0.0887293754050147 ] } } } }