# nocturne-v1-teacher by Stratus Labs: Open-Weight Model Source: https://savrn.com/models/nocturne-v1-teacher Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve nocturne-v1-teacher (88M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.2 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [nocturne-v1-teacher on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/nocturne-v1-teacher/gpus) ## Model Card By Stratus Labs, published under cc-by-4.0, revision 4ce0969cada4. ### Nocturne v1.1 (Teacher) — Bioacoustic Species Recognition for Non-Bird Taxa Nocturne is a bioacoustic species classifier trained by Stratus Labs covering the taxa that BirdNET and Perch don't: insects, amphibians, non-bird mammals, and reptiles. It's the "night side" of the soundscape — the taxa that are dominantly nocturnal or crepuscular, whose acoustic signal is the half of biodiversity monitoring bird-focused models leave behind. v1.1 (this revision) uses a 3× higher learning rate than v1 during backbone fine-tuning. Independent runs at both LRs plateaued around macro-F1 0.10; v1.1 edged past by ~3 %. Prior v1 weights are preserved in the commit history if you want to pin to revision=. [Read the full model card (1,137 words)](https://savrn.com/models/nocturne-v1-teacher/card) ## Configuration Model type nocturne_ast ## Identity and Version Repository stratus-labs/nocturne-v1-teacher Publisher Stratus Labs Task Audio classification Modality Audio Library transformers Parameters 88M parameters Languages en Revision 4ce0969cada4b111b615f3650e2b1ecd619cf835 First published 2026-08-28 Last updated 2026-09-24 ## Files and Weights 9 files, 351.9 MB in total. The weights are 1 file totalling 351.6 MB in safetensors. Weights1 file · 351.6 MB Configuration5 files · 261.3 KB Tokenizer1 file · 67.2 KB Documentation1 file · 9.7 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 351.6 MB | 5391ca66444c | | config.json | Configuration | 147.9 KB | — | | eval_report.json | Configuration | 1.2 KB | — | | model.py | Configuration | 6.1 KB | — | | thresholds.json | Configuration | 105.3 KB | — | | training_config.yaml | Configuration | 738 B | — | | README.md | Documentation | 9.7 KB | — | | .gitattributes | Repository | 1.5 KB | — | | vocab.json | Tokenizer | 67.2 KB | — | ## License and Download License cc-by-4.0 Access Open weights, no gate Download size 351.6 MB [Download from Stratus Labs](https://huggingface.co/stratus-labs/nocturne-v1-teacher) Released by Stratus Labs through its official repository on Hugging Face. [Read the license](https://creativecommons.org/licenses/by/4.0/). ## Built From - Trained on (disclosed) InsectSet459 - Trained on (disclosed) iNat-Sounds-2024 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 351.6 MB | | 16-bit | 0.2 GB | | 8-bit | 0.1 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About nocturne-v1-teacher ### How much GPU memory does nocturne-v1-teacher need? About 0.2 GB at 16-bit and 0.1 GB at 4-bit: the weights (88M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run nocturne-v1-teacher on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use nocturne-v1-teacher commercially? Yes. nocturne-v1-teacher is released under Creative Commons Attribution 4.0. CC BY 4.0 permits sharing and adapting the work, including commercially, provided the creator is credited and changes are indicated. ## Similar Models Model · Audio classification ### [nocturne-v1.2d-teacher](https://savrn.com/models/nocturne-v1-2d-teacher) [Stratus Labs](https://savrn.com/model-publishers/stratus-labs) Audio Spectrogram Transformer, ~86M parameters, 2,196 output columns. This is the first candidate in the Nocturne line to clear our pre-committed release gate against the v1 teacher. It got there by fixing two supervision bugs, not by adding data — which is the most useful thing in this card. Read the limitations section before deploying it. On an unseen recording site this model is substantially worse than v1, and our much smaller distilled student beats it outright on the very test it was released for. Both are stated with numbers below. Identical 13,710-clip held-out test set, per-class thresholds calibrated on validation, scored over the 2,182 name-aligned core classes. Rows are… Open weights cc-by-4.0 88M parameters transformers [View model](https://savrn.com/models/nocturne-v1-2d-teacher) Model · Audio classification ### [ast-finetuned-audioset-10-10-0.4593](https://savrn.com/models/ast-finetuned-audioset-10-10-0-4593) [Massachusetts Institute of Technology](https://savrn.com/model-publishers/mit) Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. It was introduced in the paper AST: Audio Spectrogram Transformer by Gong et al. and first released in this repository. Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. The Audio Spectrogram Transformer is equivalent to ViT, but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks. You can use the raw model for classifying audio into one of the AudioSet classes. See… Open weights bsd-3-clause 87M parameters transformers [View model](https://savrn.com/models/ast-finetuned-audioset-10-10-0-4593) Model · Audio classification ### [beewatch_ast_3class](https://savrn.com/models/beewatch-ast-3class) [Jethro Tababa](https://savrn.com/model-publishers/troyskie) This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 1e-05 - trainbatchsize: 16 - evalbatchsize: 16 - lrschedulertype: linear - lrschedulerwarmupsteps: 10 - numepochs: 4 - mixedprecisiontraining: Native AMP - Transformers 5.16.1 - Pytorch 2.11.0+cu128 - Datasets 4.8.5 - Tokenizers 0.23.1 Open weights bsd-3-clause 86M parameters transformers [View model](https://savrn.com/models/beewatch-ast-3class) Model · Audio classification ### [ast-finetuned-audioset-14-14-0.443](https://savrn.com/models/ast-finetuned-audioset-14-14-0-443) [Massachusetts Institute of Technology](https://savrn.com/model-publishers/mit) Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. It was introduced in the paper AST: Audio Spectrogram Transformer by Gong et al. and first released in this repository. Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. The Audio Spectrogram Transformer is equivalent to ViT, but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks. You can use the raw model for classifying audio into one of the AudioSet classes. See… Open weights bsd-3-clause 86M parameters transformers [View model](https://savrn.com/models/ast-finetuned-audioset-14-14-0-443) Model · Audio classification ### [discogs-maest-10s-pw-129e](https://savrn.com/models/discogs-maest-10s-pw-129e) [Music Technology Group (Universitat Pompeu Fabra)](https://savrn.com/model-publishers/mtg-upf) MAEST is a family of Transformer models based on PASST and focused on music analysis applications. The MAEST models are also available for inference in the Essentia library and for inference and training in the official repository. You can try the MAEST interactive demo on replicate. MAEST is a music audio representation model pre-trained on the task of music style classification. According to the evaluation reported in the original paper, it reports good performance in several downstream music analysis tasks. The MAEST models can make predictions for a taxonomy of 400 music styles derived from the public metadata of Discogs. The MAEST models have reported good performance in downstream… Open weights cc-by-nc-sa-4.0 86M parameters transformers [View model](https://savrn.com/models/discogs-maest-10s-pw-129e) Model · Audio classification ### [ced-base](https://savrn.com/models/ced-base) [Speech Team, Xiaomi MiLM Plus](https://savrn.com/model-publishers/mispeech) CED are simple ViT-Transformer-based models for audio tagging, achieving sota performance on Audioset. Notable differences from other available models include: 1. Simplification for finetuning: Batchnormalization of Mel-Spectrograms. During finetuning one does not need to first compute mean/variance over the dataset, which is common for AST. 1. Support for variable length inputs. Most other models use a static time-frequency position embedding, which hinders the model's generalization to segments shorter than 10s. Many previous transformers simply pad their input to 10s in order to avoid the performance impact, which in turn slows down training/inference drastically. 1. Training/Inference… Open weights apache-2.0 86M parameters transformers [View model](https://savrn.com/models/ced-base) ## Stratus Labs [All models and datasets](https://savrn.com/model-publishers/stratus-labs) ## Versions - [4ce0969cada4](https://savrn.com/models/nocturne-v1-teacher/versions/4ce0969cada4) · current 2026-09-24 ## Explore More - [All audio classification models](https://savrn.com/models/tasks/audio-classification) - [All models under cc-by-4.0](https://savrn.com/models/licenses/cc-by-4-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-09-24. - [Hugging Face record](https://huggingface.co/stratus-labs/nocturne-v1-teacher) - [How the hub is built](https://savrn.com/model-hub/methodology)