Zum Inhalt springen
ModelAufgelistetExtern
Browse files

Vevo2 Models

Speech & Singing Voice Synthesis · Conversion · Editing · Style Transfer · Melody Control

Quellehuggingface.co/AEmotionStudio/vevo2-models/tree/e97c9596cb4c2ea47e7dbff0664126cf19729d70
ArtText modelBasismodellRMSnow/Vevo2VersionCBewertung

Modellquelle

Art
Text model
Dateigröße
9,00 KB–1,35 GB
Basismodell
RMSnow/Vevo2
Version
vRevision e97c959
Aktualisiert
31. Okt. 2026
Downloads
16
Quelle
Hugging Face

Quellenbeschreibung

Vevo2 Models (Mæstræa Mirror)

Speech & Singing Voice Synthesis · Conversion · Editing · Style Transfer · Melody Control

Original Weights by RMSnow · Source Code by OpenMMLab / Amphion · MIT License

Mirror of the inference-only files from RMSnow/Vevo2, packaged for use with the Mæstræa AI Workstation. Training artifacts (optimizer.pt, scheduler.pt, rng_state_*.pth, trainer_state.json, training_args.bin, the _text FM variant, and the pretrained AR baseline) are dropped to keep the download lean. All credit for the model itself goes to the upstream authors.

What's in This Repo

PathDescriptionSize
contentstyle_modeling/posttrained/model.safetensorsAR transformer (Qwen2.5-0.5B post-trained)~970 MB
acoustic_modeling/fm_emilia101k_singnet7k_repa/model.safetensorsFlow-Matching transformer (~350M params)~1.4 GB
acoustic_modeling/fm_emilia101k_singnet7k_repa/whisper_stats.ptPer-channel mean/std for normed Whisper features~12 KB
vocoder/model*.safetensorsVocos vocoder (~250M, sharded)~1.2 GB
tokenizer/contentstyle_fvq16384_12.5hz/model.safetensorsContent-style tokenizer (FVQ16384 @ 12.5 Hz)~234 MB
tokenizer/prosody_fvq512_6.25hz/model.safetensorsProsody tokenizer (FVQ512 @ 6.25 Hz)~261 MB
contentstyle_modeling/posttrained/{tokenizer.json, vocab.json, ...}AR text tokenizer + configs~22 MB
*/config.json, amphion_config.json, etc.Per-component configssmall

Total: ~4 GB

Whisper-medium (~1.5 GB, used by the content-style tokenizer at inference time) is not mirrored here — openai-whisper will pull it to ~/.cache/whisper on first run.

What Vevo2 Does

Vevo2 is a unified, controllable speech-and-singing voice generation system from the Amphion toolkit. The Mæstræa panel exposes six task tabs that all route to the same backend pipeline:

  • Convert — voice/timbre conversion, FM-only (fastest)
  • TTS — zero-shot text-to-speech / text-to-singing from a short reference clip
  • Edit — rewrite words while preserving voice, melody, prosody, and style
  • Style — singing style transfer (e.g. breathy → vibrato, pop → opera) preserving voice + melody
  • Melody — sing target lyrics over a humming, whistled, or instrumental melody
  • SVC — full singing voice conversion via the AR + FM pipeline (deeper than Convert)

Architecture

  • AR Model (Qwen2.5-0.5B post-trained) — autoregressive content-style modeling
  • Flow-Matching Transformer (~350M) — acoustic generation
  • Vocos Vocoder (~250M) — high-quality 24 kHz waveform synthesis
  • Content-style + Prosody Tokenizers — FVQ codecs over Whisper / chromagram features

VRAM Requirements

Reference LengthVRAM (GPU, FP16)
15 s~6 GB
30 s~10 GB
45 s~12 GB

Recommendation: keep the timbre reference between 15–45 s. Longer references buy more identity fidelity at a real VRAM cost.

Usage in Mæstræa

The Mæstræa runner clones open-mmlab/Amphion to ~/.maestraea/libs/amphion/ on first model load and imports the pipeline from models.svc.vevo2.vevo2_utils.Vevo2InferencePipeline. The download manager pulls these weights to ~/.maestraea/models/vevo2/ and the runner resolves checkpoints from that directory at the paths shown in the table above.

For the standalone Amphion path, see the upstream Vevo2 README.

License

MIT, inherited from upstream. Commercial use of generated audio is permitted. Don't clone someone's voice without their consent.

Quellen

1 Quelle
Hugging FacePrimärVersion e97c9596cb4c2ea47e7dbff0664126cf19729d70
huggingface.co/AEmotionStudio/vevo2-models/tree/e97c9596cb4c2ea47e7dbff0664126cf19729d70

Verifiziert 31. Okt.

Download files

Repository files

File inventory only; completeness is unverified.

Modellartefakte

6 Artefakte

acoustic_modeling/fm_emilia101k_singnet7k_repa/model.safetensors

safetensors · FP32 (unverified) · 1,35 GB · SHA-256 ef3733b3f92c…7186 · Hugging Face

Download file

acoustic_modeling/fm_emilia101k_singnet7k_repa/whisper_stats.pt

pt · 9,00 KB · SHA-256 6117052b3e23…a519 · Hugging Face

Download file

contentstyle_modeling/posttrained/model.safetensors

safetensors · BF16 (unverified) · 971 MB · SHA-256 b056f8b4f061…cf16 · Hugging Face

Download file

vocoder/model_1.safetensors

safetensors · 66,5 MB · SHA-256 850799d78699…0af6 · Hugging Face

Download file

vocoder/model_2.safetensors

safetensors · 172 MB · SHA-256 56130fd13d5f…87f8 · Hugging Face

Download file

vocoder/model.safetensors

safetensors · 973 MB · SHA-256 5b5d1a46b193…56d3 · Hugging Face

Download file

Quellenauszüge

3 Auszüge
Readme14. Aug.huggingface.co/AEmotionStudio/vevo2-models

--- license: mit tags: - audio - voice-conversion - singing-voice - speech-synthesis - text-to-speech - vevo2 - amphion - safetensors - maestraea pipeline_tag: audio-to-audio base_model: RMSnow/Vevo2 --- # Vevo2 Models (Mæstræa Mirror) **Speech & Singing Voice Synthesis · Conversion · Editing · Style Transfer · Melody Control** [Original Weights](https://huggingface.co/RMSnow/Vevo2) by [RMSnow](https://huggingface.co/RMSnow) · [Source Code](https://github.com/open-mmlab/Amphion/tree/main/models/svc/vevo2) by [OpenMMLab / Amphion](https://github.com/open-mmlab/Amphion) · MIT License > Mirror of the inference-only files from `RMSnow/Vevo2`, packaged for use with the [Mæstræa AI Workstation](https://github.com/AEmotionStudio/Maestraea). Training artifacts (`optimizer.pt`, `scheduler.pt`, `rng_state_*.pth`, `trainer_state.json`, `training_args.bin`, the `_text` FM variant, and the `pretrained` AR baseline) are dropped to keep the download lean. All credit for the model itself goes to the upstream authors. ## What's in This Repo | Path | Description | Size | |------|-------------|------| | `contentstyle_modeling/posttrained/model.safetensors` | AR transformer (Qwen2.5-0.5B post-trained) | ~970 MB | | `acoustic_modeling/fm_emilia101k_singnet7k_repa/model.safetensors` | Flow-Matching transformer (~350M params) | ~1.4 GB | | `acoustic_modeling/fm_emilia101k_singnet7k_repa/whisper_stats.pt` | Per-channel mean/std for normed Whisper features | ~12 KB | | `vocoder/model*.safetensors` | Vocos vocoder (~250M, sharded) | ~1.2 GB | | `tokenizer/contentstyle_fvq16384_12.5hz/model.safetensors` | Content-style tokenizer (FVQ16384 @ 12.5 Hz) | ~234 MB | | `tokenizer/prosody_fvq512_6.25hz/model.safetensors` | Prosody tokenizer (FVQ512 @ 6.25 Hz) | ~261 MB | | `contentstyle_modeling/posttrained/{tokenizer.json, vocab.json, …}` | AR text tokenizer + configs | ~22 MB | | `*/config.json`, `amphion_config.json`, etc. | Per-component configs | small | **Total: ~4 GB** > Whisper-medium (~1.5 GB, used by the content-style tokenizer at inference time) is **not** mirrored here — `openai-whisper` will pull it to `~/.cache/whisper` on first run. ## What Vevo2 Does Vevo2 is a unified, controllable speech-and-singing voice generation system from the Amphion toolkit. The Mæstræa panel exposes six task tabs that all route to the same backend pipeline: - **Convert** — voi...

Note31. Okt.huggingface.co/AEmotionStudio/vevo2-models

Source context: 16 downloads · 2 likes · Pipeline audio-to-audio · Repo AEmotionStudio/vevo2-models

Note14. Aug.huggingface.co/AEmotionStudio/vevo2-models

Source context: 1 downloads · 2 likes · Pipeline audio-to-audio · Repo AEmotionStudio/vevo2-models