{ "experiment": "8-6", "execution_acceptance": "PASS", "execution_gates": { "orpheus_128_train_examples": true, "orpheus_16_held_out_examples": true, "orpheus_60_optimizer_steps": true, "orpheus_remote_adapter_sha256_verified": true, "orpheus_16_valid_comparison_files": true, "sesame_128_train_examples": true, "sesame_tag_categories_present": true, "sesame_60_optimizer_steps": true, "sesame_remote_adapter_sha256_verified": true, "sesame_24_valid_comparison_files": true }, "hypothesis_results": { "orpheus_held_out_loss_decreased": true, "orpheus_cross_sentence_timbre_proxy_improved": false, "sesame_held_out_loss_decreased": true, "sesame_adapted_mean_tag_score_is_positive": true, "sesame_tag_sensitivity_improved_over_base": true }, "quality_claim": "No human naturalness or voice-identity quality claim; automatic metrics are reproducible proxies only.", "remote_adapter_verification": { "orpheus": { "repository": "https://huggingface.co/bojieli/exp8-6-orpheus-elise-lora", "revision": "536092e9479fa1717e2b8f9cc1be52728b273e95", "expected_sha256": "fbd43cd5287a4b69398c29f88286e60146e9328cb48e3c22e15a2a305b25b29f", "downloaded_sha256": "fbd43cd5287a4b69398c29f88286e60146e9328cb48e3c22e15a2a305b25b29f", "verified": true }, "sesame": { "repository": "https://huggingface.co/bojieli/exp8-6-sesame-elise-tags-lora", "revision": "f2e042be0f38d6078976ef7e16cf49b91097f756", "expected_sha256": "23994b467b319f99bbc642f4dc2ba4d39718838cd7cbfe949311a42ebcb5480e", "downloaded_sha256": "23994b467b319f99bbc642f4dc2ba4d39718838cd7cbfe949311a42ebcb5480e", "verified": true } }, "orpheus": { "base": { "audio_count": 8, "valid_audio_count": 8, "mean_pairwise_mfcc_cosine": 0.9886267249073301, "min_pairwise_mfcc_cosine": 0.9738007187843323, "pairwise": [ { "prompt_a": 1, "prompt_b": 7, "cosine": 0.9738007187843323 }, { "prompt_a": 3, "prompt_b": 7, "cosine": 0.9751747846603394 }, { "prompt_a": 5, "prompt_b": 7, "cosine": 0.9768423438072205 }, { "prompt_a": 1, "prompt_b": 6, "cosine": 0.9821145534515381 }, { "prompt_a": 5, "prompt_b": 6, "cosine": 0.9832608699798584 }, { "prompt_a": 0, "prompt_b": 7, "cosine": 0.9844203591346741 }, { "prompt_a": 3, "prompt_b": 4, "cosine": 0.9847696423530579 }, { "prompt_a": 4, "prompt_b": 5, "cosine": 0.985227644443512 }, { "prompt_a": 2, "prompt_b": 7, "cosine": 0.9852697849273682 }, { "prompt_a": 1, "prompt_b": 4, "cosine": 0.9852963089942932 }, { "prompt_a": 3, "prompt_b": 6, "cosine": 0.9860416650772095 }, { "prompt_a": 0, "prompt_b": 6, "cosine": 0.9888354539871216 }, { "prompt_a": 0, "prompt_b": 1, "cosine": 0.9906319379806519 }, { "prompt_a": 0, "prompt_b": 5, "cosine": 0.9906508326530457 }, { "prompt_a": 0, "prompt_b": 4, "cosine": 0.991395890712738 }, { "prompt_a": 3, "prompt_b": 5, "cosine": 0.9918218851089478 }, { "prompt_a": 1, "prompt_b": 3, "cosine": 0.9923202395439148 }, { "prompt_a": 1, "prompt_b": 2, "cosine": 0.9923385977745056 }, { "prompt_a": 2, "prompt_b": 3, "cosine": 0.9924396276473999 }, { "prompt_a": 4, "prompt_b": 7, "cosine": 0.9930636882781982 }, { "prompt_a": 2, "prompt_b": 4, "cosine": 0.9931535124778748 }, { "prompt_a": 2, "prompt_b": 5, "cosine": 0.9931651949882507 }, { "prompt_a": 6, "prompt_b": 7, "cosine": 0.9940599799156189 }, { "prompt_a": 2, "prompt_b": 6, "cosine": 0.9941393136978149 }, { "prompt_a": 0, "prompt_b": 3, "cosine": 0.9943145513534546 }, { "prompt_a": 0, "prompt_b": 2, "cosine": 0.994386613368988 }, { "prompt_a": 4, "prompt_b": 6, "cosine": 0.9950653314590454 }, { "prompt_a": 1, "prompt_b": 5, "cosine": 0.9975469708442688 } ] }, "adapted": { "audio_count": 8, "valid_audio_count": 8, "mean_pairwise_mfcc_cosine": 0.9867024081093925, "min_pairwise_mfcc_cosine": 0.9688550233840942, "pairwise": [ { "prompt_a": 1, "prompt_b": 5, "cosine": 0.9688550233840942 }, { "prompt_a": 0, "prompt_b": 5, "cosine": 0.9705199003219604 }, { "prompt_a": 3, "prompt_b": 5, "cosine": 0.9741944670677185 }, { "prompt_a": 5, "prompt_b": 6, "cosine": 0.9782752990722656 }, { "prompt_a": 4, "prompt_b": 5, "cosine": 0.9795999526977539 }, { "prompt_a": 5, "prompt_b": 7, "cosine": 0.9798238277435303 }, { "prompt_a": 0, "prompt_b": 7, "cosine": 0.9805128574371338 }, { "prompt_a": 1, "prompt_b": 2, "cosine": 0.9849662184715271 }, { "prompt_a": 0, "prompt_b": 6, "cosine": 0.9854229688644409 }, { "prompt_a": 0, "prompt_b": 2, "cosine": 0.9863125681877136 }, { "prompt_a": 0, "prompt_b": 4, "cosine": 0.9869258999824524 }, { "prompt_a": 1, "prompt_b": 4, "cosine": 0.9872470498085022 }, { "prompt_a": 2, "prompt_b": 3, "cosine": 0.9892308115959167 }, { "prompt_a": 0, "prompt_b": 1, "cosine": 0.9895753860473633 }, { "prompt_a": 2, "prompt_b": 7, "cosine": 0.9899733662605286 }, { "prompt_a": 3, "prompt_b": 6, "cosine": 0.9900691509246826 }, { "prompt_a": 0, "prompt_b": 3, "cosine": 0.9903662800788879 }, { "prompt_a": 1, "prompt_b": 3, "cosine": 0.9910094141960144 }, { "prompt_a": 3, "prompt_b": 4, "cosine": 0.9911966323852539 }, { "prompt_a": 2, "prompt_b": 6, "cosine": 0.9914029836654663 }, { "prompt_a": 2, "prompt_b": 5, "cosine": 0.9914451241493225 }, { "prompt_a": 1, "prompt_b": 7, "cosine": 0.9918804168701172 }, { "prompt_a": 4, "prompt_b": 6, "cosine": 0.9921923279762268 }, { "prompt_a": 2, "prompt_b": 4, "cosine": 0.9927540421485901 }, { "prompt_a": 1, "prompt_b": 6, "cosine": 0.992949903011322 }, { "prompt_a": 3, "prompt_b": 7, "cosine": 0.993278980255127 }, { "prompt_a": 6, "prompt_b": 7, "cosine": 0.9935612678527832 }, { "prompt_a": 4, "prompt_b": 7, "cosine": 0.9941253066062927 } ] }, "adapted_minus_base_mean_pairwise_mfcc_cosine": -0.0019243167979375864 }, "sesame": { "classifier": "MIT/ast-finetuned-audioset-10-10-0.4593", "labels": { "laugh": { "id": 16, "name": "Laughter" }, "giggle": { "id": 18, "name": "Giggle" }, "sigh": { "id": 26, "name": "Sigh" } }, "base": { "audio_count": 12, "valid_audio_count": 12, "mean_tagged_minus_neutral": 0.00013129252571767816, "positive_pair_count": 3, "pairs": [ { "pair_id": "giggle_0", "tag": "giggle", "neutral_score": 0.0009356054943054914, "tagged_score": 0.0006116584991104901, "tagged_minus_neutral": -0.00032394699519500136 }, { "pair_id": "giggle_1", "tag": "giggle", "neutral_score": 0.0008636609418317676, "tagged_score": 0.0005855335621163249, "tagged_minus_neutral": -0.00027812737971544266 }, { "pair_id": "laugh_0", "tag": "laugh", "neutral_score": 0.0003021236334461719, "tagged_score": 0.0003340380499139428, "tagged_minus_neutral": 3.1914416467770934e-05 }, { "pair_id": "laugh_1", "tag": "laugh", "neutral_score": 0.0002934956573881209, "tagged_score": 0.0007533965981565416, "tagged_minus_neutral": 0.0004599009407684207 }, { "pair_id": "sigh_0", "tag": "sigh", "neutral_score": 0.0034571753349155188, "tagged_score": 0.006142919883131981, "tagged_minus_neutral": 0.002685744548216462 }, { "pair_id": "sigh_1", "tag": "sigh", "neutral_score": 0.0024482603184878826, "tagged_score": 0.0006605299422517419, "tagged_minus_neutral": -0.0017877303762361407 } ] }, "adapted": { "audio_count": 12, "valid_audio_count": 12, "mean_tagged_minus_neutral": 0.001097210906057929, "positive_pair_count": 4, "pairs": [ { "pair_id": "giggle_0", "tag": "giggle", "neutral_score": 0.001688887132331729, "tagged_score": 0.0017779936315491796, "tagged_minus_neutral": 8.910649921745062e-05 }, { "pair_id": "giggle_1", "tag": "giggle", "neutral_score": 0.003269059816375375, "tagged_score": 0.0007443267968483269, "tagged_minus_neutral": -0.002524733019527048 }, { "pair_id": "laugh_0", "tag": "laugh", "neutral_score": 0.00026441123918630183, "tagged_score": 0.0012162356870248914, "tagged_minus_neutral": 0.0009518244478385895 }, { "pair_id": "laugh_1", "tag": "laugh", "neutral_score": 0.00033708245609886944, "tagged_score": 0.0003236289485357702, "tagged_minus_neutral": -1.3453507563099265e-05 }, { "pair_id": "sigh_0", "tag": "sigh", "neutral_score": 0.0017972267232835293, "tagged_score": 0.006373145151883364, "tagged_minus_neutral": 0.0045759184285998344 }, { "pair_id": "sigh_1", "tag": "sigh", "neutral_score": 0.0010693982476368546, "tagged_score": 0.004574000835418701, "tagged_minus_neutral": 0.0035046025877818465 } ] }, "adapted_minus_base_mean_tag_sensitivity": 0.0009659183803402508, "scores": [ { "arm": "base", "pair_id": "laugh_0", "condition": "neutral", "tag": "laugh", "audioset_label": "Laughter", "audioset_score": 0.0003021236334461719, "seconds": 2.72, "rms": 0.06748455762863159, "path": "audio/sesame/base/laugh_0_neutral.wav" }, { "arm": "base", "pair_id": "laugh_0", "condition": "tagged", "tag": "laugh", "audioset_label": "Laughter", "audioset_score": 0.0003340380499139428, "seconds": 6.0, "rms": 0.06531786173582077, "path": "audio/sesame/base/laugh_0_tagged.wav" }, { "arm": "base", "pair_id": "laugh_1", "condition": "neutral", "tag": "laugh", "audioset_label": "Laughter", "audioset_score": 0.0002934956573881209, "seconds": 2.08, "rms": 0.23473648726940155, "path": "audio/sesame/base/laugh_1_neutral.wav" }, { "arm": "base", "pair_id": "laugh_1", "condition": "tagged", "tag": "laugh", "audioset_label": "Laughter", "audioset_score": 0.0007533965981565416, "seconds": 3.84, "rms": 0.03746151924133301, "path": "audio/sesame/base/laugh_1_tagged.wav" }, { "arm": "base", "pair_id": "giggle_0", "condition": "neutral", "tag": "giggle", "audioset_label": "Giggle", "audioset_score": 0.0009356054943054914, "seconds": 1.68, "rms": 0.14035280048847198, "path": "audio/sesame/base/giggle_0_neutral.wav" }, { "arm": "base", "pair_id": "giggle_0", "condition": "tagged", "tag": "giggle", "audioset_label": "Giggle", "audioset_score": 0.0006116584991104901, "seconds": 2.96, "rms": 0.08793672919273376, "path": "audio/sesame/base/giggle_0_tagged.wav" }, { "arm": "base", "pair_id": "giggle_1", "condition": "neutral", "tag": "giggle", "audioset_label": "Giggle", "audioset_score": 0.0008636609418317676, "seconds": 2.96, "rms": 0.049566783010959625, "path": "audio/sesame/base/giggle_1_neutral.wav" }, { "arm": "base", "pair_id": "giggle_1", "condition": "tagged", "tag": "giggle", "audioset_label": "Giggle", "audioset_score": 0.0005855335621163249, "seconds": 5.92, "rms": 0.0142013905569911, "path": "audio/sesame/base/giggle_1_tagged.wav" }, { "arm": "base", "pair_id": "sigh_0", "condition": "neutral", "tag": "sigh", "audioset_label": "Sigh", "audioset_score": 0.0034571753349155188, "seconds": 2.32, "rms": 0.06743967533111572, "path": "audio/sesame/base/sigh_0_neutral.wav" }, { "arm": "base", "pair_id": "sigh_0", "condition": "tagged", "tag": "sigh", "audioset_label": "Sigh", "audioset_score": 0.006142919883131981, "seconds": 6.0, "rms": 0.05658983066678047, "path": "audio/sesame/base/sigh_0_tagged.wav" }, { "arm": "base", "pair_id": "sigh_1", "condition": "neutral", "tag": "sigh", "audioset_label": "Sigh", "audioset_score": 0.0024482603184878826, "seconds": 2.24, "rms": 0.014161595143377781, "path": "audio/sesame/base/sigh_1_neutral.wav" }, { "arm": "base", "pair_id": "sigh_1", "condition": "tagged", "tag": "sigh", "audioset_label": "Sigh", "audioset_score": 0.0006605299422517419, "seconds": 3.36, "rms": 0.010387708432972431, "path": "audio/sesame/base/sigh_1_tagged.wav" }, { "arm": "adapted", "pair_id": "laugh_0", "condition": "neutral", "tag": "laugh", "audioset_label": "Laughter", "audioset_score": 0.00026441123918630183, "seconds": 3.92, "rms": 0.0402710996568203, "path": "audio/sesame/adapted/laugh_0_neutral.wav" }, { "arm": "adapted", "pair_id": "laugh_0", "condition": "tagged", "tag": "laugh", "audioset_label": "Laughter", "audioset_score": 0.0012162356870248914, "seconds": 3.6, "rms": 0.06890808790922165, "path": "audio/sesame/adapted/laugh_0_tagged.wav" }, { "arm": "adapted", "pair_id": "laugh_1", "condition": "neutral", "tag": "laugh", "audioset_label": "Laughter", "audioset_score": 0.00033708245609886944, "seconds": 2.48, "rms": 0.13957583904266357, "path": "audio/sesame/adapted/laugh_1_neutral.wav" }, { "arm": "adapted", "pair_id": "laugh_1", "condition": "tagged", "tag": "laugh", "audioset_label": "Laughter", "audioset_score": 0.0003236289485357702, "seconds": 3.76, "rms": 0.051783934235572815, "path": "audio/sesame/adapted/laugh_1_tagged.wav" }, { "arm": "adapted", "pair_id": "giggle_0", "condition": "neutral", "tag": "giggle", "audioset_label": "Giggle", "audioset_score": 0.001688887132331729, "seconds": 2.0, "rms": 0.11314665526151657, "path": "audio/sesame/adapted/giggle_0_neutral.wav" }, { "arm": "adapted", "pair_id": "giggle_0", "condition": "tagged", "tag": "giggle", "audioset_label": "Giggle", "audioset_score": 0.0017779936315491796, "seconds": 2.72, "rms": 0.07838206738233566, "path": "audio/sesame/adapted/giggle_0_tagged.wav" }, { "arm": "adapted", "pair_id": "giggle_1", "condition": "neutral", "tag": "giggle", "audioset_label": "Giggle", "audioset_score": 0.003269059816375375, "seconds": 3.28, "rms": 0.10014152526855469, "path": "audio/sesame/adapted/giggle_1_neutral.wav" }, { "arm": "adapted", "pair_id": "giggle_1", "condition": "tagged", "tag": "giggle", "audioset_label": "Giggle", "audioset_score": 0.0007443267968483269, "seconds": 4.88, "rms": 0.07103203237056732, "path": "audio/sesame/adapted/giggle_1_tagged.wav" }, { "arm": "adapted", "pair_id": "sigh_0", "condition": "neutral", "tag": "sigh", "audioset_label": "Sigh", "audioset_score": 0.0017972267232835293, "seconds": 2.72, "rms": 0.09723222255706787, "path": "audio/sesame/adapted/sigh_0_neutral.wav" }, { "arm": "adapted", "pair_id": "sigh_0", "condition": "tagged", "tag": "sigh", "audioset_label": "Sigh", "audioset_score": 0.006373145151883364, "seconds": 3.92, "rms": 0.1117464229464531, "path": "audio/sesame/adapted/sigh_0_tagged.wav" }, { "arm": "adapted", "pair_id": "sigh_1", "condition": "neutral", "tag": "sigh", "audioset_label": "Sigh", "audioset_score": 0.0010693982476368546, "seconds": 2.32, "rms": 0.15041208267211914, "path": "audio/sesame/adapted/sigh_1_neutral.wav" }, { "arm": "adapted", "pair_id": "sigh_1", "condition": "tagged", "tag": "sigh", "audioset_label": "Sigh", "audioset_score": 0.004574000835418701, "seconds": 3.36, "rms": 0.07697359472513199, "path": "audio/sesame/adapted/sigh_1_tagged.wav" } ] } }