Home

Awesome

bioacoustics-model-zoo

Pre-trained models for bioacoustic classification tasks

Set up / Installation

To use the bioacoustics model zoo:

  1. create a python environment (3.9-3.11 supported) using conda or your preferred package manager

  2. install the required packages: download the requirements.txt file, then run pip install -r /path/to/requirements.txt

  3. Use the models in any of the following ways:

Use the torch.hub API to access models:

import torch
model = torch.hub.load('kitzeslab/bioacoustics-model-zoo','Perch')

Use the opensoundscape API:

from opensoundscape.ml import bioacoustics_model_zoo as bmz
model = bmz.load('Perch')

Install this repository as a Python package,

Installing as a package may be necessary to overcome issues with num_workers>0, per this issue.

For example, you can install the repo as a package in a python environment using pip:

pip install git+https://github.com/kitzeslab/bioacoustics-model-zoo

If you want to intall a specific branch or release of the model zoo, for instance release 0.11.0, add an @ then the tag at the end of the command:

pip install git+https://github.com/kitzeslab/bioacoustics-model-zoo@0.11.0

You can now use the package directly in python:

import bioacoustics_model_zoo as bmz
model = bmz.HawkEars()

Basic usage

List:

List available models in the GitHub repo bioacoustics-model-zoo

import torch
torch.hub.list('kitzeslab/bioacoustics-model-zoo')

Load:

Get a ready-to-use model object: choose from the models listed in the previous command

model = torch.hub.load('kitzeslab/bioacoustics-model-zoo','rana_sierrae_cnn',trust_repo=True)

Inference:

model is an OpenSoundscape CNN object (or other class) which you can use as normal.

For instance, use the model to generate predictions on an audio file:

audio_file_path = './hydrophone_10s.wav'
scores = model.predict([audio_file_path],activation_layer='softmax')
scores

Contributing

To contribute a model to the model zoo, email sam.lapp@pitt.edu or add a model yourself:

Model list

Perch:

Embedding and bird classification model trained on Xeno Canto

Example:

import torch
model = torch.hub.load('kitzeslab/bioacoustics-model-zoo', 'Perch',trust_repo=True)
predictions = model.predict(['test.wav']) # predict on the model's classes
embeddings = model.embed(['test.wav']) # generate embeddings on each 5 sec of audio

BirdNET

Classification and embedding model trained on a large set of annotated bird vocalizations

Additional required packages:

tensorflow, tensorflow_hub

Example:

import torch
m = torch.hub.load('kitzeslab/bioacoustics-model-zoo', 'BirdNET',trust_repo=True)
m.predict(['test.wav']) # returns dataframe of per-class scores
m.embed(['test.wav']) # returns dataframe of embeddings

HawkEars

Bird classification CNN for 314 North American species

Additional required packages:

timm, torchaudio

Example:

import torch
m = torch.hub.load('kitzeslab/bioacoustics-model-zoo', 'HawkEars',trust_repo=True)
m.predict(['test.wav']) # returns dataframe of per-class scores
m.embed(['test.wav']) # returns dataframe of embeddings

MixIT Bird SeparationModel

Separate audio into channels potentially representing separate sources.

This particular model was trained on bird vocalization data.

Additional required packages:

tensorflow, tensorflow_hub

Example:

First, download the checkpoint and metagraph from the MixIt Github repo: install gsutil then run the following command in your terminal:

gsutil -m cp -r gs://gresearch/sound_separation/bird_mixit_model_checkpoints .

Then, use the model in python:

import torch
# provide the local path to the checkpoint when creating the object
model = torch.hub.load(
    'kitzeslab/bioacoustics-model-zoo',
    'SeparationModel',
    checkpoint='/path/to/bird_mixit_model_checkpoints/output_sources4/model.ckpt-3223090',
    trust_repo=True,
) # creates 4 channels; use output_sources8 to separate into 8 channels

# separate opensoundscape Audio object into 4 channels:
# note that it seems to work best on 5 second segments
a = Audio.from_file('audio.mp3',sample_rate=22050).trim(0,5)
separated = model.separate_audio(a)

# save audio files for each separated channel:
# saves audio files with extensions like _stem0.wav, _stem1.wav, etc
model.load_separate_write('./temp.wav')

YAMNet:

Embedding model trained on AudioSet YouTube

Additional required packages:

tensorflow, tensorflow_hub

Example:

import torch
m = torch.hub.load('kitzeslab/bioacoustics-model-zoo', 'YAMNet',trust_repo=True)
m.predict(['test.wav']) # returns dataframe of per-class scores
m.embed(['test.wav']) # returns dataframe of embeddings

rana_sierrae_cnn:

Detect underwater vocalizations of Rana sierrae, the Sierra Nevada Yellow-legged Frog

example:

import torch
m = torch.hub.load('kitzeslab/bioacoustics-model-zoo', 'rana_sierrae_cnn',trust_repo=True)
m.predict(['test.wav']) # returns dataframe of per-class scores

Other automated detection tools for bioacoustics

RIBBIT

Detect sounds with periodic pulsing patterns.

Implemented in OpenSoundscape as opensoundscape.ribbit.ribbit().

Accelerating and decelerating sequences

Detect pulse trains that accelerate, such as the drumming of Ruffed Grouse (Bonasa umbellus)

Implemented in OpenSoundscape as

opensoundscape.signal_processing.detect_peak_sequence_cwt().

(note that in earlier versions of OpenSoundscape the module is named signal rather than signal_processing)

Troubleshooting

TensorFlow Installation in Python Environment

Some models in the model zoo require tensorflow (and potentially tensorflow_hub) to be installed in your python environment.

Installing TensorFlow can be tricky, and it may not be possible to have cuda-enabled tensorflow in the same environment as cuda-enabled pytorch. In this case, you can install a cpu-only version of tensorflow (pip install tensorflow-cpu). You may want to start with a fresh environment, or uninstall tensorflow and nvidia-cudnn-cu11 then reinstall pytorch with the appropriate nvidia-cudnn-cu11, to avoid having the wrong cudnn for PyTorch.

Alternatively, if you want to use the TensorFlow Hub models with GPU acceleration, create an environment where you uninstall pytorch and nvidia-cudnn-cu11 and install a cpu-only version (see this page for the correct installation command). Then, you can pip install tensorflow-hub and let it choose the correct nvidia-cudnn so that it can use CUDA and leverage GPU acceleration.

Installing tensorflow: Carefully follow the directions for your system. Note that models provided in this repo might require the specific nvidia-cudnn-cu11 version 8.6.0, which could conflict with the version required for pytorch.

Error while Downloading TF Hub Models

Some of the models provided in this repo are hosted on the Tensorflow model hub.

If you encounter the following error (or similar) when downloading a TensorFlow Hub model:

ValueError: Trying to load a model of incompatible/unknown type. '/var/folders/d8/265wdp1n0bn_r85dh3pp95fh0000gq/T/tfhub_modules/9616fd04ec2360621642ef9455b84f4b668e219e' contains neither 'saved_model.pb' nor 'saved_model.pbtxt'.

You need to delete the folder listed in the error message (something like /var/folders/...tfhub_modules/....). After deleting that folder, downloading the model should work.

The issue occurs because TensorFlow Hub is looking for a cached model in a temporary folder where it was once stored but no longer exists. See relevant GitHub issue here: https://github.com/tensorflow/hub/issues/896