Update README.md

README.md

 # Cross-species F0 estimation, dataset and study of baseline algorithms
 
 ## Use a crepe model pretrained on animal signals to analyse your own signals
+Install the packages necessary to run a crepe model using `pip install -r predict_requirements.txt`
+
 Use the `predict.py` script to run a pretrained crepe model to estimate fundamental frequency values for your own sounds.
 ```
 usage: predict.py [-h] [--model_path MODEL_PATH] [--compress COMPRESS] [--step STEP] [--decoder {argmax,weighted_argmax,viterbi}] [--print PRINT] indir
@@ -21,6 +23,8 @@ optional arguments:
 
 ## Reproduce paper experiments
 
+Python package requirements necessary to run the paper experiments are detailled in the `requirements.txt` file.
+
 ### metadata.py
 Stores a dictionary of datasets and characteristics (SR, NFFT, path to access soundfiles, and downsampling factor for ultra/infra-sonic signals)
 Convenient to iterate over the whole dataset