vggish-keras 0.0.19

VGGish in Keras.

VGGish: A VGG-like audio classification model

This repository provides a VGGish model, implemented in Keras with tensorflow backend (since tf.slim is deprecated, I think we should have an up-to-date interface). This repository is developed based on the model for AudioSet. For more details, please visit the slim version.

Install

pip install vggish-keras

Weights will be downloaded the first time they are requested. You can also run python -m vggish_keras.download_helpers.download_weights which will download them.

NOTE: Currently - this relies on a pending change to pumpp in https://github.com/bmcfee/pumpp/pull/123. To get those changes, you need

pip install git+https://github.com/beasteers/pumpp@tf_keras

Usage

import librosa
import numpy as np
import vggish_keras as vgk

# define the model
pump = vgk.get_pump()
model = vgk.VGGish(pump)

# transform audio into VGGish embeddings without fc layers
X = pump.transform(librosa.util.example_audio_file())[vgk.params.PUMP_INPUT]
X = np.concatenate([X]*5)
Z = model.predict(X)

# calculate timestamps
op = pump['mel']
ts = np.arange(len(Z)) / op.sr * op.hop_length
assert Z.shape == (5, 512)

Reference:

• Gemmeke, J. et. al., AudioSet: An ontology and human-labelled dataset for audio events, ICASSP 2017

• Hershey, S. et. al., CNN Architectures for Large-Scale Audio Classification, ICASSP 2017

I include a weight conversion script in download_helpers/convert_ckpt.py which shows how I converted the weights from .ckpt to .h5 for those that are interested.

TODO

• currently, parameters (sample rate, hop size, etc) can be changed globally via vgk.params - I'd like to allow for parameter overrides to be passed to vgk.VGGish