SoulX-Singer Models (Safetensors Mirror)
Safetensors conversion of Soul-AILab/SoulX-Singer weights for use in the MAESTRO AI Workstation.
Models
| Path | Size | Description |
|---|---|---|
| svs/model.safetensors | ~2.82 GB | Singing Voice Synthesis (lyrics+MIDI → singing) |
| svc/model.safetensors | ~2.79 GB | Singing Voice Conversion (audio-to-audio) |
| whisper-base/ | ~0.29 GB | Verbatim openai/whisper-base (Apache-2.0) — the SVC model's frozen semantic encoder. Its weights are not in the SVC checkpoint; bundling them here keeps SVC fully offline. |
| config.yaml | 579 B | Model architecture configuration |
| phone_set.json | ~30 KB | Phoneme mapping for SVS |
Preprocessing assets
The SVS annotation pipeline (vocal separation → RMVPE F0 → lyric ASR → ROSVOT note transcription) pulls its component weights on demand from the companion repo AEmotionStudio/soulx-singer-preprocess (verbatim upstream files from the SoulX-Singer-Preprocess release).
Architecture
- Flow-matching based (F5-TTS foundation)
- 22-layer transformer with 1024 hidden size, 16 heads
- 128-dim mel spectrogram, 24kHz output
- Trained on 42,000+ hours of aligned vocals (Mandarin, English, Cantonese)
Conversion notes
svs/andsvc/aretorch.load(ckpt)["state_dict"]→ safetensors conversions of upstreammodel.pt/model-svc.pt; loaders consume them withstrict=True.whisper-base/is byte-identical to upstream openai/whisper-base (sha256-verified at upload; seebackend/scripts/mirror_soulx_singer_to_hf.pyin MAESTRO).
License
Apache 2.0
- Downloads last month
- 9