braindecode/duin-pretrained
feature-extraction model by braindecode
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
braindecode-native re-host of the official Du-IN pretrained checkpoints (Zheng et al., NeurIPS 2024), converted so they load directly with braindecode.models.DuIN. Du-IN decodes speech (61 Chinese words) from sEEG. Each subject's signal (10 selected bipolar channels, 1000 Hz) goes through a subject-specific spatial projection, a patch-wise convolutional tokenizer (one token per 100 ms) and an 8-layer Transformer encoder. The encoder is pretrained per subject by masked modelling of discrete codes learned by a VQ-VAE (mae); the VQ-VAE encoder itself (vqvae) is the other released stage. These weights are a format conversion only of the authors' checkpoints, with no re-training. For each of the 24 checkpoints: subject layer W (160, 1), reshaped to spatialprojection.weight (16, 10)); same input to < 1e-5 (max abs diff 7.2e-6 over all 24); outputs as loading the original .pth. The pretraining-only parts (maskemb, VQ codebook, MAE token head) are dropped. The classification head (headhidden, finallayer, 61 outputs)…
Read the full model card ↗ · Preview checked 2026-11-20T07:06:20.556Z
Inside the original model card — Document outline
- Du-IN — braindecode weights
- Provenance
- Files
- Training data
- Usage
- Replication (braindecode PR #1298)
- License
- Citation
- Cite Braindecode
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: cc-by-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
braindecode/duin-pretrained is a feature-extraction model repository published by braindecode on Hugging Face. The source reports the braindecode library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- feature-extraction
- Library
- braindecode
- Recent downloads (30 days)
- 118,445
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 4,183,357
- Architecture
- Not reported
- License
- cc-by-4.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-11T17:39:29.000Z
- Last modified
- 2026-11-09T10:30:38.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-20T07:05:14.871Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.