VoxCPM2 — inference mirror for MAESTRO
Inference-ready repack of openbmb/VoxCPM2 (OpenBMB), kept by AEmotionStudio so the MAESTRO DAW can fetch the checkpoint on demand. The model is not fine-tuned or otherwise altered — this repo only repacks the upstream weights for loading:
model.safetensors— the 2B tokenizer-free diffusion-AR stack (LocEnc → MiniCPM-4 TSLM → RALM → LocDiT), verbatim from upstream (bf16 storage, sha256-checked; bf16 confirmed by MAESTRO's same-seed fp16-vs-bf16 whisper-gate against a seed-to-seed null baseline).audiovae.safetensors— AudioVAE V2 (16 kHz encode → 48 kHz decode), converted from the pickledaudiovae.pthviasafetensors.save_model(the VAE usesweight_norm, whoseweight_g/weight_valiasing a baresave_filewould corrupt).config.json,tokenizer.json,special_tokens_map.json— verbatim.tokenizer_config.json— verbatim minus the list-formextra_special_tokenskey (crashes some transformers loaders; the tokens are already registered intokenizer.json, so dropping the key is lossless).- upstream's
tokenization_voxcpm2.pyis omitted — inference loads a plainLlamaTokenizerFast; notrust_remote_codeanywhere. sha256.json— checksums of every file in this repo.
| Component | Purpose |
|---|---|
model.safetensors | LocEnc + MiniCPM-4 2B TSLM + RALM + LocDiT |
audiovae.safetensors | AudioVAE V2 (latents → 48 kHz mono waveform) |
| tokenizer files | LlamaTokenizerFast vocabulary + config |
VoxCPM2 is a tokenizer-free diffusion-autoregressive TTS at native 48 kHz: 30 languages plus 9 Chinese dialects with no language tags, voice design from a text description, and three cloning tiers (reference clip / reference + style directive / reference + transcript).
License
- Code: Apache-2.0 (OpenBMB/VoxCPM).
- Weights (this repo): Apache-2.0 — inherited unchanged from upstream.
Credit for the model belongs entirely to the OpenBMB team; this mirror exists only for reliable on-demand delivery into MAESTRO.