Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,3 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
## Citation
|
| 2 |
|
| 3 |
```bibtex
|
|
@@ -7,6 +67,6 @@
|
|
| 7 |
year = {2026},
|
| 8 |
publisher = {Hugging Face},
|
| 9 |
journal = {Hugging Face Hub},
|
| 10 |
-
howpublished = {\url{https://huggingface.co/
|
| 11 |
}
|
| 12 |
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
tags:
|
| 4 |
+
- karaoke
|
| 5 |
+
- audio
|
| 6 |
+
- captions
|
| 7 |
+
- music
|
| 8 |
+
- songs
|
| 9 |
+
pipeline_tag: audio-to-audio
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Karaoke Songs Long
|
| 13 |
+
|
| 14 |
+
A dataset of **long-form karaoke instrumental tracks** with auto-generated captions describing the musical characteristics of each song. This repository contains audio-to-text caption pairs for long-duration karaoke versions of popular songs.
|
| 15 |
+
|
| 16 |
+
## What it is
|
| 17 |
+
|
| 18 |
+
This dataset provides instrumental karaoke tracks (long versions — extended or full-length) paired with descriptive captions. Each caption details the genre, tempo (BPM), instrumentation, mood, and potential use cases of the audio.
|
| 19 |
+
|
| 20 |
+
## Dataset Contents
|
| 21 |
+
|
| 22 |
+
The `captions.csv` file contains the following fields:
|
| 23 |
+
|
| 24 |
+
| Field | Description |
|
| 25 |
+
|-------|-------------|
|
| 26 |
+
| `original_filename` | Original audio filename (artist - song title - karaoke version) |
|
| 27 |
+
| `cleaned_filename` | Cleaned/standardized filename |
|
| 28 |
+
| `caption` | Auto-generated textual description of the audio track |
|
| 29 |
+
|
| 30 |
+
### Included Artists (sampling)
|
| 31 |
+
|
| 32 |
+
- 50 Cent — "In Da Club" (Karaoke)
|
| 33 |
+
- 5 Seconds of Summer — "Amnesia", "Beside You", "Don't Stop", "Good Girls", "Heartbreak Girl", "She's Kinda Hot", "Youngblood"
|
| 34 |
+
- A Great Big World & Christina Aguilera — "Say Something"
|
| 35 |
+
- Adele — "Chasing Pavements", "Don't You Remember", "Easy On Me"
|
| 36 |
+
- *(and many more)*
|
| 37 |
+
|
| 38 |
+
### Caption Features
|
| 39 |
+
|
| 40 |
+
Each caption includes information about:
|
| 41 |
+
- **Genre**: e.g., pop rock, hip hop, indie rock, folk, electronic, soul/R&B
|
| 42 |
+
- **Tempo**: BPM range (e.g., 72 BPM, 84 BPM, 120 BPM, 160 BPM)
|
| 43 |
+
- **Time Signature**: typically 4/4
|
| 44 |
+
- **Instrumentation**: guitars, bass, drums, synths, piano, etc.
|
| 45 |
+
- **Mood/Atmosphere**: energetic, reflective, calming, introspective, uplifting
|
| 46 |
+
- **Use Cases**: background music, workout, documentaries, soundtracks, commercials
|
| 47 |
+
|
| 48 |
+
## Usage
|
| 49 |
+
|
| 50 |
+
This dataset is suitable for:
|
| 51 |
+
- **Audio captioning** and music description models
|
| 52 |
+
- **Text-to-audio** generation training
|
| 53 |
+
- **Music information retrieval** (MIR) research
|
| 54 |
+
- **Karaoke applications** and instrument separation
|
| 55 |
+
- **Audio retrieval** from natural language queries
|
| 56 |
+
|
| 57 |
+
## License
|
| 58 |
+
|
| 59 |
+
Please check the individual song copyrights and terms. This repository contains descriptive captions only; actual audio files (if present) are instrumental karaoke tracks and may be subject to additional licensing.
|
| 60 |
+
|
| 61 |
## Citation
|
| 62 |
|
| 63 |
```bibtex
|
|
|
|
| 67 |
year = {2026},
|
| 68 |
publisher = {Hugging Face},
|
| 69 |
journal = {Hugging Face Hub},
|
| 70 |
+
howpublished = {\url{https://huggingface.co/edwixx/karaoke_songs_long}}
|
| 71 |
}
|
| 72 |
```
|