Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
stratus-labs
/
nocturne-v1.2-teacher
Like
0
Follow
Stratus Labs
1
Audio Classification
PyTorch
InsectSet459
iNat-Sounds-2024
AnuraSet
English
bioacoustics
audio-spectrogram-transformer
ecology
biodiversity
species-identification
non-bird
orthoptera
cicadidae
amphibian
anuran
passive-acoustic-monitoring
conservation
License:
cc-by-4.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
nocturne-v1.2-teacher
352 MB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
stratusvale
Retire hosted demo/API (2026-09-27); link the Stratus Labs research page
8e31cde
verified
9 days ago
.gitattributes
Safe
1.52 kB
initial commit
27 days ago
README.md
Safe
7.17 kB
Retire hosted demo/API (2026-09-27); link the Stratus Labs research page
9 days ago
best.pt
352 MB
xet
Nocturne v1.2 teacher — first in the family to beat v1 (core calibrated macro-F1 0.1511 vs 0.1488, mAP 0.1541 vs 0.1498). Multi-hot targets + val-mAP selection; epoch 18/40.
27 days ago
config.yaml
Safe
1.27 kB
Nocturne v1.2 teacher — first in the family to beat v1 (core calibrated macro-F1 0.1511 vs 0.1488, mAP 0.1541 vs 0.1498). Multi-hot targets + val-mAP selection; epoch 18/40.
27 days ago
eval_report.json
Safe
3.75 kB
Nocturne v1.2 teacher — first in the family to beat v1 (core calibrated macro-F1 0.1511 vs 0.1488, mAP 0.1541 vs 0.1498). Multi-hot targets + val-mAP selection; epoch 18/40.
27 days ago
final_test_trainprotocol.json
Safe
338 Bytes
Nocturne v1.2 teacher — first in the family to beat v1 (core calibrated macro-F1 0.1511 vs 0.1488, mAP 0.1541 vs 0.1498). Multi-hot targets + val-mAP selection; epoch 18/40.
27 days ago
model.py
Safe
6.11 kB
Nocturne v1.2 teacher — first in the family to beat v1 (core calibrated macro-F1 0.1511 vs 0.1488, mAP 0.1541 vs 0.1498). Multi-hot targets + val-mAP selection; epoch 18/40.
27 days ago
run_manifest.json
Safe
483 Bytes
Nocturne v1.2 teacher — first in the family to beat v1 (core calibrated macro-F1 0.1511 vs 0.1488, mAP 0.1541 vs 0.1498). Multi-hot targets + val-mAP selection; epoch 18/40.
27 days ago
thresholds.json
Safe
106 kB
Nocturne v1.2 teacher — first in the family to beat v1 (core calibrated macro-F1 0.1511 vs 0.1488, mAP 0.1541 vs 0.1498). Multi-hot targets + val-mAP selection; epoch 18/40.
27 days ago
vocab.json
Safe
67.7 kB
Nocturne v1.2 teacher — first in the family to beat v1 (core calibrated macro-F1 0.1511 vs 0.1488, mAP 0.1541 vs 0.1498). Multi-hot targets + val-mAP selection; epoch 18/40.
27 days ago
