Python Module to process and predict on music attributes
Two Models were built and trained to predict valence given an audio sample. One uses a feature pipeline on top of librosa to make a number of predictors that go into a Random Forest model to determine a valence prediction. The other uses OpenAI's whisper model to transcribe lyrics, then tokenize the words, and again a trained Random Forest model makes the prediction based on lyrics.
| Model RMSE | |
|---|---|
| Audio | 1.56 |
| Lyrics | 1.28 |
Data Used:
- 1000 Song Dataset - Download here
- Spotify Developer API - 30 second previews
Package Requirements
pip install -r requirements.txt
- make sure to download whisper from openai (not currently included in requirements.txt)
- Also must install ffmpeg (using brew, choco, etc.)
1 maintainer
Release files for audiologic 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| audiologic-0.1.1.tar.gz | 6.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| audiologic-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 14.6 kB
Release files / audiologic-0.1.1.tar.gz
| Download URL | audiologic-0.1.1.tar.gz |
|---|---|
| Size | 6.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c481eb0336923406ac7e00689fd5c414dcbfb1e64230e63a60ac5b3dd6b7c286
|
|
BLAKE2b-256 checksum How to use checksums |
a47757cce8bb2de67f364e0be12730e9e21da084f731e464b8eb3a8ea35be316
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.8.10
|
Release files / audiologic-0.1.1-py3-none-any.whl
| Download URL | audiologic-0.1.1-py3-none-any.whl |
|---|---|
| Size | 7.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e9cae3a0129b1bed34b9e111d22c22e60c8ed924d990991e360e2071257b2617
|
|
BLAKE2b-256 checksum How to use checksums |
54a88928b5246247705dcdefc1e43448e31e97038695524c7725517bc3cc9b09
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.8.10
|
