soykertje/spleeter 🖼️ → ❓

▶️ 794.1K runs 📅 Aug 2023 ⚙️ Cog 0.8.3 🔗 GitHub 📄 Paper ⚖️ License
audio-to-audio music-source-separation

About

Spleeter is Deezer source separation library with pretrained models written in Python and uses Tensorflow.

Example Output

Output

{"vocals":"https://pbxt.replicate.delivery/wUbjzNe8z0zDRKSnvD3YeA7UnSf2rfC8ANcJL83YQGsIZX4FB/vocals.wav","accompaniment":"https://pbxt.replicate.delivery/UyWAC41T81aJOFMvEuedXEJzCi4ne0fWTA4Xa4TdDNQmsL8iA/accompaniment.wav"}

Performance Metrics

9.04s Prediction Time
9.07s Total Time
Input Parameters
audio (required) Type: string
Audio file
Output Schema

Output

Example Execution Logs 
INFO:spleeter:File /tmp/tmpqqw8u2di/vocals.wav written succesfully
INFO:spleeter:File /tmp/tmpqqw8u2di/accompaniment.wav written succesfully
Version Details
Version ID
cd128044253523c86abfd743dea680c88559ad975ccd72378c8433f067ab5d0a
Version Created
August 27, 2023
Run on Replicate →