Fingerprint audio files & identify what's playing

In this repository, we adapt the open-source implementation for the one-vs-one experiments.

How to set up

Run $ make clean reset to clean & init database struct
Run $ make tests to make sure that everything is properly configurated
Copy some .mp3 audio files into mp3/ directory
Run $ make fingerprint-songs to analyze audio files & fill your db with hashes
Start play any of audio file (from any source) from mp3/ directory, and run (parallely) $ make recognize-listen seconds=5

To remove a specific song & related hash from db

$ python sql-execute.py -q "DELETE FROM songs WHERE id = 6;"
$ python sql-execute.py -q "DELETE FROM fingerprints WHERE song_fk = 6;"

Name		Name	Last commit message	Last commit date
Latest commit History 55 Commits
db		db
libs		libs
tests		tests
.editorconfig		.editorconfig
.gitignore		.gitignore
Makefile		Makefile
README.md		README.md
Shazam_constellation.ipynb		Shazam_constellation.ipynb
audio-fingerprint-identifying-python.iml		audio-fingerprint-identifying-python.iml
collect-fingerprints-of-songs.py		collect-fingerprints-of-songs.py
compare_two_files.py		compare_two_files.py
config-development.sample.json		config-development.sample.json
config.json		config.json
get-database-stat.py		get-database-stat.py
one_vs_one_experiment.py		one_vs_one_experiment.py
one_vs_one_experiment_subset_full.py		one_vs_one_experiment_subset_full.py
recognize-from-file.py		recognize-from-file.py
recognize-from-microphone.py		recognize-from-microphone.py
recognize.ipynb		recognize.ipynb
requirements.txt		requirements.txt
reset-database.py		reset-database.py
songs_in_db.py		songs_in_db.py
sql-execute.py		sql-execute.py