WIP. Inference code is not ready yet!

SoulX-Singer GGUF

Upstream model: Soul-AILab/SoulX-Singer, revision 40493ad90286056c7a9095035164434a79daa8c9.

ROSVOT preprocessing

Offline singing-note transcription for audio.cpp. One F32 package contains ROSVOT, RWBD word-boundary prediction and RMVPE pitch extraction. Outputs are MIDI or JSON note events; lyric transcription and streaming are not supported.

Checkpoint source: Soul-AILab/SoulX-Singer-Preprocess, revision 83dc50289d22a81b1e9998f5b9e111aef7c1fdcd. Reference implementation: ROSVOT, commit 3c8332bf43adae35f6e4d64971862f2f6139b310. The source model card declares Apache-2.0 for the checkpoint distribution; ROSVOT reference code is MIT licensed. License notices are embedded in the GGUF.

audiocpp_cli --task midi --family rosvot \
  --model ROSVOT-GGUF/rosvot-f32.gguf \
  --backend cuda --threads 8 --audio singing.wav --out notes.mid --log

Use --request-option output_format=json --out notes.json for note pitches, start/end seconds and word indices. An optional word_durations_file JSON array provides word timing instead of predicted RWBD boundaries. Use isolated vocals.

Validated on CPU, CUDA and Vulkan. CPU component parity passes the strict FP32 comparison; GPU rounding can change discrete note boundaries. This is a note-transcription model, not a guarantee of perfect musical transcription.

(WIP)

Downloads last month
7
GGUF
Model size
0.1B params
Architecture
audiocpp
Hardware compatibility
Log In to add your hardware

32-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for audio-cpp/SoulX-Singer-GGUF

Quantized
(2)
this model