wq2012
/

ls_conformer_small_ext_softmax

Feature Extraction

speaker-verification

speaker-recognition

speaker-embeddings

extended_set_softmax

Model card Files Files and versions

ls_conformer_small_ext_softmax / config.json

Commit History

Oct 25 4 days ago

04:19
v0.4.0: full-convergence checkpoints (S_safe = X + 2 epochs), TFLite exports, and updated evaluation archives

wq2012

Verified signature
8e64598

Oct 22 7 days ago

02:50
v0.3.0: training-crop provenance (fixed T=180 crops for the released weights; step-0 loss fingerprint; training_provenance block; variable_length_training aligned with the weights), TFLite EER CIs and re-measured latencies, flaxspeaker>=0.3.0 quickstart

wq2012

Verified signature
b49d8b9

Oct 20 9 days ago

15:24
Round 2: honest model card (training budget, variant labels, Vox1-O 10-spk subset, TFLite window, deviations), cleaned config.json, 26 dB Vox1-O subset metrics; remove misleading preprocessor_config.json

wq2012

Verified signature
54bc09e

Oct 18 11 days ago

03:23
Round 2 sync: portable config.json and official VoxCeleb1-O eval_results.json

wq2012

Verified signature
8c19994
02:55
Round 2: Add scoring_type/loss_type/vad_config to config.json and voxceleb1_o_official to eval_results.json

wq2012

Verified signature
9e252ef

Oct 15 14 days ago

01:38
Upload FlaxSpeaker pretrained model ls_conformer_small_ext_softmax

wq2012

Verified signature
da3a19c