README.md
| 1 | --- |
| 2 | license: apache-2.0 |
| 3 | metrics: |
| 4 | - accuracy |
| 5 | - roc_auc |
| 6 | base_model: |
| 7 | - facebook/wav2vec2-base-960h |
| 8 | --- |
| 9 | [Music genre](https://en.wikipedia.org/wiki/Music_genre) classification is a fundamental and versatile application in many various domains. Some possible use cases for music genre classification include: |
| 10 | |
| 11 | - music recommendation systems; |
| 12 | - content organization and discovery; |
| 13 | - radio broadcasting and programming; |
| 14 | - music licensing and copyright management; |
| 15 | - music analysis and research; |
| 16 | - content tagging and metadata enrichment; |
| 17 | - audio identification and copyright protection; |
| 18 | - music production and creativity; |
| 19 | - healthcare and therapy; |
| 20 | - entertainment and gaming. |
| 21 | |
| 22 | The model is trained based on publicly available dataset of labeled music data — [GTZAN Dataset](https://www.kaggle.com/datasets/andradaolteanu/gtzan-dataset-music-genre-classification) — that contains 1000 sample 30-second audio files evenly split among 10 genres: |
| 23 | |
| 24 | - blues; |
| 25 | - classical; |
| 26 | - country; |
| 27 | - disco; |
| 28 | - hip-hop; |
| 29 | - jazz; |
| 30 | - metal; |
| 31 | - pop; |
| 32 | - reggae; |
| 33 | - rock. |
| 34 | |
| 35 | The final code is available as a [Kaggle notebook](https://www.kaggle.com/code/dima806/music-genre-classification-wav2vec2-base-960h). |
| 36 | See also [my Medium article](https://medium.com/data-and-beyond/building-a-free-advanced-music-genre-classification-pipeline-using-machine-learning-654b0de7cc3e) for more details. |