mtg/music-arousal-valence 📝🖼️❓ → 🖼️

▶️ 17.5K runs 📅 Jun 2022 ⚙️ Cog 0.9.9 🔗 GitHub ⚖️ License
music-emotion-recognition music-understanding

Performance

7.9sTypical run time
17.5KTotal runs

About

Regression of musical arousal and valence values

Example Output

Output

Example output

Performance Metrics

7.91s Prediction Time
15.39s Total Time
All Input Parameters 
{
  "audio": "https://replicate.delivery/mgxm/907f9b45-185c-41b1-96af-f2742bada25b/rock.mp3",
  "dataset": "emomusic",
  "embedding_type": "msd-musicnn"
}
Input Parameters
url Type: string
YouTube URL to process (overrides audio input)
audio Type: string
Audio file to process
dataset Default: emomusic
Arousal/Valence training dataset
output_format Default: Visualization
Output either a bar chart visualization or a JSON blob
embedding_type Default: msd-musicnn
Embedding type to use: vggish, or musicnn
Output Schema

Output

Type: string • Format: uri

Version Details
Version ID
9ae3915e0727ccad372d2608fe076cad87437306da79876df695c82a63149175
Version Created
February 17, 2025
Run on Replicate →