ls_conformer_tiny_ge2e / eval_results.json
wq2012's picture
Round 2: Add scoring_type/loss_type/vad_config to config.json and voxceleb1_o_official to eval_results.json
0af6a6a verified
Raw History Blame Contribute Delete
7.38 kB
{
"experiment_name": "ls_conformer_tiny_ge2e",
"train_dataset": "librispeech",
"backbone": "conformer",
"size_variant": "tiny",
"pooling_type": "atp",
"loss_type": "ge2e_softmax",
"scoring_type": "cosine",
"embedding_dim": 128,
"num_parameters": 693126,
"num_steps": 400,
"train_time_sec": 288.25,
"initial_loss": 2.09,
"final_loss": 0.3523,
"in_domain_eval": {
"eer": 0.1053333333333333,
"eer_percent": 10.5333,
"eer_ci95_low_percent": 9.4,
"eer_ci95_high_percent": 11.5333,
"eer_threshold": 0.6059616804122925,
"min_dcf_001": 0.772,
"min_dcf_005": 0.6207,
"min_dcf_01": 0.4893,
"roc_auc": 0.9608,
"num_trials": 3000,
"num_unique_utterances": 999,
"latency_ms_per_utterance": 17.21,
"eval_time_sec": 18.924,
"scoring_type": "cosine"
},
"multi_enroll_3utt_eval": {
"eer": 0.06200000000000003,
"eer_percent": 6.2,
"eer_ci95_low_percent": 4.8,
"eer_ci95_high_percent": 7.9525,
"eer_threshold": 0.664314866065979,
"min_dcf_001": 0.488,
"min_dcf_005": 0.34,
"min_dcf_01": 0.28,
"roc_auc": 0.9845,
"num_trials": 1000
},
"cross_dataset_eval": {
"voxceleb1_o_official": {
"eer": 0.2852944113071049,
"eer_percent": 28.5294,
"eer_ci95_low_percent": 26.5376,
"eer_ci95_high_percent": 30.4945,
"eer_threshold": 0.58367520570755,
"min_dcf_001": 0.9843,
"min_dcf_005": 0.9339,
"min_dcf_01": 0.9199,
"roc_auc": 0.7957,
"num_trials": 2500,
"num_unique_utterances": 937,
"latency_ms_per_utterance": 4.289,
"eval_time_sec": 4.567,
"scoring_type": "cosine",
"num_target_trials": 1789,
"num_impostor_trials": 711,
"num_unseen_speakers": 10,
"protocol": "veri_test2_speaker_disjoint_10spk_2500trials"
},
"cnceleb2_zero_shot": {
"eer": 0.30000000000000004,
"eer_percent": 30.0,
"eer_ci95_low_percent": 28.6492,
"eer_ci95_high_percent": 31.8667,
"eer_threshold": 0.6296399831771851,
"min_dcf_001": 0.9993,
"min_dcf_005": 0.9993,
"min_dcf_01": 0.9547,
"roc_auc": 0.7787,
"num_trials": 3000,
"num_unique_utterances": 739,
"latency_ms_per_utterance": 17.479,
"eval_time_sec": 14.073,
"scoring_type": "cosine"
}
},
"config_yaml": "configs/ls_conformer_tiny_ge2e.yml",
"multi_domain_eval": {
"domains_1utt": {
"librispeech": {
"eer": 0.1053333333333333,
"eer_percent": 10.5333,
"eer_ci95_low_percent": 9.4,
"eer_ci95_high_percent": 11.5333,
"eer_threshold": 0.6059616804122925,
"min_dcf_001": 0.772,
"min_dcf_005": 0.6207,
"min_dcf_01": 0.4893,
"roc_auc": 0.9608,
"num_trials": 3000,
"num_unique_utterances": 999,
"latency_ms_per_utterance": 17.21,
"eval_time_sec": 18.924,
"scoring_type": "cosine"
},
"cnceleb2": {
"eer": 0.30000000000000004,
"eer_percent": 30.0,
"eer_ci95_low_percent": 28.6492,
"eer_ci95_high_percent": 31.8667,
"eer_threshold": 0.6296399831771851,
"min_dcf_001": 0.9993,
"min_dcf_005": 0.9993,
"min_dcf_01": 0.9547,
"roc_auc": 0.7787,
"num_trials": 3000,
"num_unique_utterances": 739,
"latency_ms_per_utterance": 17.479,
"eval_time_sec": 14.073,
"scoring_type": "cosine"
},
"voxceleb1": {
"eer": 0.257,
"eer_percent": 25.7,
"eer_ci95_low_percent": 23.9,
"eer_ci95_high_percent": 27.4763,
"eer_threshold": 0.5478366613388062,
"min_dcf_001": 0.938,
"min_dcf_005": 0.918,
"min_dcf_01": 0.895,
"roc_auc": 0.8282,
"num_trials": 2000,
"num_unique_utterances": 250,
"latency_ms_per_utterance": 21.465,
"eval_time_sec": 6.525,
"scoring_type": "cosine"
},
"universal_pooled": {
"eer": 0.219125,
"eer_percent": 21.9125,
"eer_ci95_low_percent": 21.05,
"eer_ci95_high_percent": 22.8125,
"eer_threshold": 0.6035156846046448,
"min_dcf_001": 0.9968,
"min_dcf_005": 0.899,
"min_dcf_01": 0.8525,
"roc_auc": 0.8711,
"num_trials": 8000,
"num_unique_utterances": 1988,
"latency_ms_per_utterance": 0.0,
"eval_time_sec": 3.448,
"scoring_type": "cosine"
},
"voxceleb1_o_official": {
"eer": 0.2852944113071049,
"eer_percent": 28.5294,
"eer_ci95_low_percent": 26.5376,
"eer_ci95_high_percent": 30.4945,
"eer_threshold": 0.58367520570755,
"min_dcf_001": 0.9843,
"min_dcf_005": 0.9339,
"min_dcf_01": 0.9199,
"roc_auc": 0.7957,
"num_trials": 2500,
"num_unique_utterances": 937,
"latency_ms_per_utterance": 4.289,
"eval_time_sec": 4.567,
"scoring_type": "cosine",
"num_target_trials": 1789,
"num_impostor_trials": 711,
"num_unseen_speakers": 10,
"protocol": "veri_test2_speaker_disjoint_10spk_2500trials"
}
},
"universal_macro_avg_1utt": {
"eer_percent": 22.08,
"min_dcf_001": 0.9031,
"min_dcf_01": 0.7797,
"roc_auc": 0.8559
},
"domains_3utt": {
"librispeech": {
"eer": 0.06200000000000003,
"eer_percent": 6.2,
"eer_ci95_low_percent": 4.8,
"eer_ci95_high_percent": 7.9525,
"eer_threshold": 0.664314866065979,
"min_dcf_001": 0.488,
"min_dcf_005": 0.34,
"min_dcf_01": 0.28,
"roc_auc": 0.9845,
"num_trials": 1000
},
"cnceleb2": {
"eer": 0.258,
"eer_percent": 25.8,
"eer_ci95_low_percent": 23.2,
"eer_ci95_high_percent": 28.8,
"eer_threshold": 0.7029243111610413,
"min_dcf_001": 0.896,
"min_dcf_005": 0.884,
"min_dcf_01": 0.862,
"roc_auc": 0.8256,
"num_trials": 1000
},
"voxceleb1": {
"eer": 0.21599999999999997,
"eer_percent": 21.6,
"eer_ci95_low_percent": 19.0,
"eer_ci95_high_percent": 23.905,
"eer_threshold": 0.6436901688575745,
"min_dcf_001": 0.91,
"min_dcf_005": 0.91,
"min_dcf_01": 0.876,
"roc_auc": 0.8708,
"num_trials": 1000
},
"universal_pooled": {
"eer": 0.1806666666666667,
"eer_percent": 18.0667,
"eer_ci95_low_percent": 16.5,
"eer_ci95_high_percent": 19.3333,
"eer_threshold": 0.6769924759864807,
"min_dcf_001": 0.8647,
"min_dcf_005": 0.8347,
"min_dcf_01": 0.7707,
"roc_auc": 0.9049,
"num_trials": 3000
}
},
"universal_macro_avg_3utt": {
"eer_percent": 17.87,
"min_dcf_001": 0.7647,
"min_dcf_01": 0.6727,
"roc_auc": 0.8936
}
},
"hf_pretrained_dir": "pretrained_models/ls_conformer_tiny_ge2e",
"hf_repo_id": "wq2012/ls_conformer_tiny_ge2e",
"hf_url": "https://huggingface.co/wq2012/ls_conformer_tiny_ge2e",
"hf_collection_url": "https://huggingface.co/collections/wq2012/flaxspeaker-6ad02d999a4180c794870595",
"voxceleb1_o_official_eer_percent": 28.5294,
"voxceleb1_o_official_min_dcf_001": 0.9843,
"voxceleb1_o_official_roc_auc": 0.7957
}