Spaces:
Runtime error
Runtime error
Added readme file.
Browse files
README.md
CHANGED
|
@@ -1,12 +1,34 @@
|
|
| 1 |
---
|
| 2 |
title: GenreClassifier
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
app_file: app.py
|
| 8 |
pinned: false
|
| 9 |
license: afl-3.0
|
| 10 |
---
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
|
|
|
|
| 1 |
---
|
| 2 |
title: GenreClassifier
|
| 3 |
+
emoji: 🎶
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: green
|
| 6 |
sdk: gradio
|
| 7 |
app_file: app.py
|
| 8 |
pinned: false
|
| 9 |
license: afl-3.0
|
| 10 |
---
|
| 11 |
|
| 12 |
+
This Genre Classifier is built using the [GTZAN dataset](https://www.kaggle.com/andradaolteanu/gtzan-dataset-music-genre-classification?select=Data) which consists of 10 genres. These genres are:
|
| 13 |
+
- Blues
|
| 14 |
+
- Classical
|
| 15 |
+
- Country
|
| 16 |
+
- Disco
|
| 17 |
+
- Hiphop
|
| 18 |
+
- Jazz
|
| 19 |
+
- Metal
|
| 20 |
+
- Pop
|
| 21 |
+
- Reggae
|
| 22 |
+
- Rock
|
| 23 |
+
|
| 24 |
+
Data for each genre includes 100 30-seconds long tracks which were then used to build a LSTM model
|
| 25 |
+
using Keras (tensorflow backend).
|
| 26 |
+
|
| 27 |
+
With more data, this model could have a more robust performance but for now,
|
| 28 |
+
it does well on GTZAN-like data.
|
| 29 |
+
|
| 30 |
+
To use this model, navigate to [the app](https://huggingface.co/spaces/Enutrof/GenreClassifier) on huggingface spaces and upload a track.
|
| 31 |
+
|
| 32 |
+
To view the API documentation and use it, click [this link](https://hf.space/gradioiframe/Enutrof/GenreClassifier/api).
|
| 33 |
+
|
| 34 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
|