meow-decoder / README.md
AtharvIITB's picture
v0.4.0: store cat ids for the weights-only benchmark; intervals in the card
9690977 verified
|
Raw History Blame Contribute Delete
2.13 kB
---
license: other
license_name: mixed-see-card
library_name: meow-decoder
pipeline_tag: audio-classification
tags: [cats, bioacoustics, meow, audio-classification]
datasets: [CatMeows]
---
# Meow Decoder classifier heads
Small logistic-regression heads that turn a meow's audio embedding into the likeliest situation:
waiting for food, enjoying attention, or stressed somewhere new. Used by
[meow-decoder](https://github.com/ATHARV-IIT-BOMBAY/meow-decoder), which downloads them automatically.
| File | Encoder | First guess right (unseen cats) | Top two | Macro recall | Calibration error | License |
|---|---|---|---|---|---|---|
| `beats.npz` | Earth Species Project `esp_aves2_sl_beats_all` | 65.9% (57–74%) | 89.1% | 58.1% | 2.2% | CC BY-NC-SA 4.0 (follows the encoder) |
| `ast.npz` | MIT AST fine-tuned on AudioSet | 61.8% (52–72%) | 84.1% | 53.2% | 4.7% | CC BY 4.0 (follows the CatMeows data) |
Always guessing the most common situation scores 50.2% (macro recall 33%). Scores are 5-fold cross-validation over
whole cats (`splits.json` in the code repo), so every test meow comes from a cat the head never saw. The range is a
95% interval from resampling cats: with 21 cats, the benchmark is small.
Re-run the benchmark from these files alone, in seconds, with no audio or audio models:
```bash
meow benchmark --from-weights
```
## Format
Plain NumPy arrays, no pickle: `classes`, `mean`, `scale`, `coef`, `intercept` (standardize, then multinomial
logistic regression), plus `X`, `y` (the 440 training embeddings, kept so the app can refit with your own cat's meows),
`cats` (which cat each embedding came from) and `train_only` (marks augmented copies; none in this release).
```python
from meow_decoder import Decoder
Decoder("beats").predict("meow.wav")["results"]
```
## Training data
[CatMeows](https://zenodo.org/records/4008297) (Ludovico et al., 2020): 440 meows from 21 Maine Coon and European
Shorthair cats, CC BY 4.0. Audio is 8 kHz, so nothing above 4 kHz was heard.
## Limits
Three situations only. It cannot detect pain or illness. Pet cats from one dataset; other cats may sound different.