Fix repo id in usage snippet; add paper/code links, results, and citation

README.md

@@ -14,9 +14,22 @@ language:
 pipeline_tag: audio-classification
 ---
 
-# ReDimNet2-B6: Speaker Verification Model
+# ReDimNet2+: Speaker Verification Model
 
-ReDimNet2-B6 is a state-of-the-art Automatic Speaker Verification (ASV) model trained for speaker recognition tasks. The model uses a ReDimNet2 backbone with Mel-spectrogram frontend and produces 192-dimensional speaker embeddings.
+ReDimNet2+ is a robustness-oriented adaptation of the compact ReDimNet2-B6 backbone for Automatic Speaker Verification (ASV), trained for robustness to channel and codec mismatch (compression, telephony codecs, noise, reverberation). The model uses a ReDimNet2 backbone with a Mel-spectrogram frontend and produces 192-dimensional speaker embeddings.
+
+- **Code (training, eval, Docker submission pipeline):** [github.com/lab260ru/redimnet2-plus](https://github.com/lab260ru/redimnet2-plus)
+- **Paper:** *ReDimNet2+ for Robust Speaker Verification under Channel and Codec Shift* (manuscript submitted to ICASSP 2027) — [report.pdf](https://github.com/lab260ru/redimnet2-plus/blob/main/report.pdf)
+
+## Results
+
+Evaluated with random 4-second windows and cosine similarity on L2-normalized embeddings (VoxCeleb1, EER %; EER<sub>p</sub> pools O/E/H; EER<sub>ph</sub> is a 26-condition codec/waveform stress test). See the paper for the full protocol and ablations.
+
+| System | EER<sub>o</sub> | EER<sub>e</sub> | EER<sub>h</sub> | EER<sub>p</sub> | EER<sub>ph</sub> |
+|---|---:|---:|---:|---:|---:|
+| ReDimNet2 baseline (public ckpt.) | 1.601 | 1.725 | 3.039 | 2.420 | 7.214 |
+| WeSpeaker CAM++ (best evaluated WeSpeaker ckpt.) | 0.787 | 0.928 | 1.824 | — | — |
+| **ReDimNet2+ LMFT (this checkpoint)** | **0.351** | **0.523** | **1.055** | **0.824** | **1.991** |
 
 ## Model Architecture
 
@@ -44,7 +57,7 @@ from huggingface_hub import hf_hub_download
 from omegaconf import OmegaConf
 
 # Download model weights
-model_path = hf_hub_download("lab260/asv-redimnet2-b6", "pytorch_model_fsdp.bin")
+model_path = hf_hub_download("lab260/redimnet2-plus", "pytorch_model_fsdp.bin")
 
 # Load checkpoint
 state_dict = torch.load(model_path, map_location="cpu")
@@ -159,18 +172,37 @@ def verify_speaker(model, audio1_path, audio2_path, threshold=0.79):
 
 ## Training
 
-The model was trained using:
-- **Dataset**: VoxCeleb2 and other speaker verification datasets
-- **Loss Function**: SphereFace2
-- **Optimizer**: AdamW
-- **Learning Rate**: 0.0003
-- **Augmentations**: SpecAugment, codec simulation
+Full recipe and code: [github.com/lab260ru/redimnet2-plus](https://github.com/lab260ru/redimnet2-plus). Summary:
+- **Initialization**: public ReDimNet2-B6 checkpoint, backbone architecture unchanged.
+- **Data**: 7 corpora, ~63.9k speakers, ~4.6M utterances, ~8,675 h — VoxBlink2, VoxCeleb2, 3D-Speaker, CN-Celeb/CN-Celeb2, TidyVoice, KeSpeech.
+- **Augmentation**: filters, additive noise (colored, MUSAN, RawBoost-style), simulated RIRs, speed perturbation, and codec simulation (MP3, Opus, AAC, FLAC, Vorbis, G.723.1, IMA ADPCM, G.722, A-law, μ-law, Speex, AMR-NB at 8/16 kHz), plus SpecAugment/CutMix.
+- **Loss Function**: SphereFace2 (one-vs-all)
+- **Optimizer**: AdamW, BFloat16, Accelerate + FSDP on 6 GPUs, gradient clipping at 20
+- **Recipe**: staged multi-corpus adaptation followed by large-margin fine-tuning (LMFT) on 6-second windows (margin 0.3)
+
+This checkpoint (`pytorch_model_fsdp.bin`) is the final **ReDimNet2+ LMFT** model from the paper.
+
+## Retrieval reranking
+
+The GitHub repo also ships a training-free, graph-based reranking stage (mean-chain + k-NN graph reranking with hubness correction) for open-set retrieval on top of these embeddings — see [`submission/reranking/`](https://github.com/lab260ru/redimnet2-plus/tree/main/submission/reranking). It raises VoxBlink2-subset Pr@k from 0.7413 to 0.7687 without retraining.
 
 ## Limitations
 
 - Model expects 16 kHz audio input
 - Maximum audio duration: 60 seconds
-- Performance may vary on noisy environments and different recording conditions
+- EER roughly doubles from VoxCeleb1-E to -H (hard impostors), and the 26-condition codec/waveform stress test (EER<sub>ph</sub>) stays above the clean metrics even after LMFT — see the paper's limitations section
+- External comparisons in the paper are shared-protocol, not equal-data comparisons
+
+## Citation
+
+```bibtex
+@unpublished{borodin2027redimnet2plus,
+  title  = {{ReDimNet2+} for Robust Speaker Verification under Channel and Codec Shift},
+  author = {Borodin, Kirill and Kudryavtsev, Vasiliy and Mkrchian, Grach},
+  year   = {2026},
+  note   = {Manuscript submitted to ICASSP 2027}
+}
+```
 
 ## License