Update README.md

README.md

@@ -9,7 +9,7 @@ tags:
 
 # Baseline model for audio classification of orthopera and hemiptera
 
-This baseline model, utilized in the ECOSoundSet paper (link will follow), was trained to tag audio files with one or more of 86 species from the Orthoptera and Hemiptera insect orders.
+This baseline model, utilized in the [ECOSoundSet paper](https://arxiv.org/abs/2504.20776), was trained to tag audio files with one or more of 86 species from the Orthoptera and Hemiptera insect orders.
 
 ## Installation
 
@@ -25,7 +25,19 @@ The model can be applied on all wav files present in a folder (`<data-root>`) an
 
 `autrainer inference hf:AlexanderGbd/insects-base-cnn10-96k-t -r <data-root> <output-root>`
 
-For possible inference settings (e.g. using sliding window) and all usable parameters, please have a look at the autrainer documentation.
+For possible inference settings (e.g. using sliding window) and all usable parameters, please have a look at the [autrainer documentation](https://autrainer.github.io/autrainer/usage/cli_reference.html#autrainer-inference).
+
+The following model usage is recommended:
+
+```autrainer inference hf:AlexanderGbd/insects-base-cnn10-96k-t /path/to/input/data /path/to/store/results -r -w 4 -s 4 -sr 96000```
+
+Here:
+- r: recursive flag (recursively go through all subfolders as well).
+- w: window size (here 4 seconds), i.e. length of the audio segment analyzed (in seconds).
+- s: step size (here 4 seconds), i.e. how far the window moves forward after each analysis (in seconds).
+- sr: target sampling rate (in Hz). If audio files don’t match this rate, they’re resampled.
+- e: file extension (default is wav), i.e. the file format to process. 
+
 
 
 ## Training
@@ -36,8 +48,7 @@ The model has been originally trained on AudioSet by Kong et. al. (https://ieeex
 
 ### Dataset
 
-The model has been further trained (finetuned) on 4s long audio segments of the ECOSoundSet dataset, which is soon to be submitted,
-and will be referenced here as soon as it is publicly available. 
+The model has been further trained (finetuned) on 4s long audio segments of the first version of the ECOSoundSet dataset. 
 
 
 ### Features