# BirdCLEF+ 2025: Bronze Medal Solution

Reference to recently Completed BirdCLEF + 2025 competition.
[https://www.kaggle.com/competitions/birdclef-2025/](https://www.kaggle.com/competitions/birdclef-2025/)
Acknowledgements:
Thanks for Competition Hosts Cornell Lab of Ornithology and Kaggle  for organizing this competition.
Also, congratulations to all the winners.
Thanks to many of the participants in this competition for active discussions, sharing ideas and sharing notebooks.
I am glad to note the completion of this competition and Bronze medal with 146th rank. I had earlier got
silver medal in BirdCLEF 2024 competition.
Solution details of my approach:
This is a high-performance solution for the BirdCLEF 2025 Kaggle competition, which involves identifying bird species from audio recordings. The notebook  implements a sophisticated two-model ensemble strategy to generate a final prediction file. It achieves this by generating two separate submissions and then blending them together. The note book is based on high scoring public notebooks shared by participants in this competition.
Key Highlights
Two-Model Ensemble Strategy: The core of the solution  is blending the outputs of two different, powerful models:
Submission 1: Uses an eca_nfnet_l0 model.
Submission 2: Uses a seresnext26t_32x4d model.
This approach leverages the diverse strengths of different architectures to produce a more robust final prediction.
Temporal Smoothing: A crucial post-processing technique is applied to the predictions. It assumes that if a bird is present in one 5-second audio chunk, it is likely to be present in the adjacent chunks. The code enforces this by smoothing the predictions using a weighted average of a chunk and its immediate neighbors (e.g., new_pred = 0.2
previous + 0.6
current + 0.2*next).
Power Adjustment for Low-Confidence Predictions: The code uses a clever function  to boost the scores of predictions that are not in the top-k most confident classes. This helps to amplify weak signals and improve the overall evaluation metric.
Final Weighted Blending: After generating two complete submission files, the notebook combines them using a final weighted average. The final weights used are [0.85, 0.3], giving more importance to the SEResNeXt model's output.
Rounding to 4 decimal Points:  We round of the final outputs to 4 decimal places. I am quoting here a practical strategy which gives good results by removing unnecessary noisy digits.
"Rounding to the nearest cent is sufficiently accurate for practical purposes."- Alexander John Ellis
In summary, solution relies on ensembling strong models and applying domain-specific post-processing (temporal smoothing) to achieve good results.
References:
Holger Klinck, Juan Sebastián Cañas, Maggie Demkin, Sohier Dane, Stefan Kahl, and Tom Denton. BirdCLEF+ 2025.
[https://kaggle.com/competitions/birdclef-2025](https://kaggle.com/competitions/birdclef-2025)
, 2025. Kaggle.
ECA-NFNet-L0 Model:
[https://huggingface.co/timm/eca_nfnet_l0](https://huggingface.co/timm/eca_nfnet_l0)
Model card for seresnext26t_32x4d.bt_in1k:
[https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)
BIRDCLEF+ 2025: Weighted Blend notebook:
[https://www.kaggle.com/code/kumarandatascientist/bird25-weightedblend-0-88](https://www.kaggle.com/code/kumarandatascientist/bird25-weightedblend-0-88)
BirdCLEF24: Silver Medal Solution :
[https://www.kaggle.com/competitions/birdclef-2024/discussion/511793](https://www.kaggle.com/competitions/birdclef-2024/discussion/511793)
The models can be extended for Endangered species of wild animals.
Usage of GPUs