Instructions to use arda-argmax/sortformer-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use arda-argmax/sortformer-finetuned with NeMo:
# tag did not correspond to a valid NeMo domain.
- Notebooks
- Google Colab
- Kaggle
metadata
library_name: nemo
tags:
- sortformer
- speaker-diarization
- automatic-speech-recognition
6spk-v0.4-ami-bs1-acc8-l4-diskcache-shardedval-v1-1778218672
Sortformer fine-tuning run, hosted under arda-argmax/sortformer-finetuned.
Best checkpoint
- monitor:
val_der(min) - best value:
0.128021 - step:
4140 - epoch:
9
Files:
best.nemo— full NeMo checkpoint (config + weights), restorable viaSortformerEncLabelModel.restore_from('best.nemo')best.json— machine-readable metadata for the best checkpointcheckpoints/step_*_epoch_*_*.nemo— archived copies of every checkpoint that became the best during trainingconfig.yaml— Hydra config the run was launched with
Run info
- started:
2026-05-08T05:39:27Z - finished:
2026-05-09T06:05:01Z - live dashboard: arda-argmax/sortformer-trackio-v2
Notes
- submitted uploads: 25
- succeeded: 25
- dropped (superseded): 0
- failed: 0