annabeth97c commited on
Commit
1bbd78d
Β·
verified Β·
1 Parent(s): 0acfe63

Update README.md

Browse files

docs: Update Readme

Files changed (1) hide show
  1. README.md +34 -26
README.md CHANGED
@@ -11,9 +11,11 @@ pinned: false
11
 
12
  # 🎼 SonicVerse
13
 
14
- An interactive demo for SonicVerse, a music captioning model, allowing users to input audio of up to 10 seconds and generate a natural language caption
15
  that includes a general description of the music as well as music features such as key, instruments, genre, mood / theme, vocals gender.
16
 
 
 
17
  ---
18
 
19
  ## πŸš€ Demo
@@ -25,7 +27,8 @@ Check out the live Space here:
25
 
26
  ## πŸš€ Samples
27
 
28
- Short captions
 
29
 
30
  ---
31
 
@@ -35,6 +38,10 @@ Short captions
35
 
36
  βœ… Upload a long music clip (upto 1 minute for successful demo) to get a long detailed caption for the whole music clip.
37
 
 
 
 
 
38
  ---
39
 
40
  ## πŸ› οΈ How to Run Locally
@@ -57,19 +64,6 @@ python app.py
57
 
58
  ---
59
 
60
- <!-- ## πŸ“‚ File Structure
61
-
62
- ```
63
- .
64
- β”œβ”€β”€ app.py # Web app file
65
- β”œβ”€β”€ requirements.txt # Python dependencies
66
- β”œβ”€β”€ environment.yml # Conda environment
67
- β”œβ”€β”€ README.md # This file
68
- └── src/sonicverse # Source
69
- ```
70
-
71
- --- -->
72
-
73
  ## πŸ’‘ Usage
74
 
75
  To use the app:
@@ -79,6 +73,31 @@ To use the app:
79
 
80
  ---
81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
  ## 🧹 Built With
83
 
84
  - [Hugging Face Spaces](https://huggingface.co/spaces)
@@ -87,14 +106,3 @@ To use the app:
87
  - [MERT 95M](https://huggingface.co/m-a-p/MERT-v1-95M)
88
  ---
89
 
90
- <!-- ## ✨ Acknowledgements
91
-
92
- - [Model authors or papers you built on]
93
- - [Contributors or collaborators]
94
-
95
- ---
96
-
97
- ## πŸ“œ License
98
-
99
- This project is licensed under the MIT License / Apache 2.0 / Other.
100
- -->
 
11
 
12
  # 🎼 SonicVerse
13
 
14
+ An interactive demo for **SonicVerse**, a music captioning model, allowing users to input audio and generate a natural language caption
15
  that includes a general description of the music as well as music features such as key, instruments, genre, mood / theme, vocals gender.
16
 
17
+ The demo supports both short (10s) and long (up to 1 minute) audio inputs.
18
+
19
  ---
20
 
21
  ## πŸš€ Demo
 
27
 
28
  ## πŸš€ Samples
29
 
30
+ Short captions and long chained LLM-generated captions:
31
+ ➑️ [Samples page](https://amaai-lab.github.io/SonicVerse/)
32
 
33
  ---
34
 
 
38
 
39
  βœ… Upload a long music clip (upto 1 minute for successful demo) to get a long detailed caption for the whole music clip.
40
 
41
+ βœ… Captions include musical attributes (key, instruments, tempo, etc.)
42
+
43
+ ⚠️ You can upload audio of any length, but due to compute limitations on Hugging Face Spaces, we recommend uploading clips under **30 seconds** unless you have a **Hugging Face Pro account** or run the app locally.
44
+
45
  ---
46
 
47
  ## πŸ› οΈ How to Run Locally
 
64
 
65
  ---
66
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  ## πŸ’‘ Usage
68
 
69
  To use the app:
 
73
 
74
  ---
75
 
76
+ ## πŸ“œ Citation
77
+
78
+ If you use SonicVerse in your work, please cite our paper:
79
+
80
+ **SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning**
81
+ Anuradha Chopra, Abhinaba Roy, Dorien Herremans
82
+ Accepted to AIMC 2025
83
+
84
+ ```bibtex
85
+ @article{chopra2025sonicverse,
86
+ title={SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning},
87
+ author={Chopra, Anuradha and Roy, Abhinaba and Herremans, Dorien},
88
+ journal={Proceedings of the 6th Conference on AI Music Creativity (AIMC 2025)},
89
+ year={2025},
90
+ address={Brussels, Belgium},
91
+ month={September},
92
+ url={https://arxiv.org/abs/2506.15154},
93
+ }
94
+ ```
95
+
96
+ Read the paper here: [arXiv:2506.15154](https://arxiv.org/abs/2506.15154)
97
+ DOI: [10.48550/arXiv.2506.15154](https://doi.org/10.48550/arXiv.2506.15154)
98
+
99
+ ---
100
+
101
  ## 🧹 Built With
102
 
103
  - [Hugging Face Spaces](https://huggingface.co/spaces)
 
106
  - [MERT 95M](https://huggingface.co/m-a-p/MERT-v1-95M)
107
  ---
108