Resonance
A from-scratch neural text-to-speech engine (SNAC 24 kHz codec), trained in the Anima project ( The published resonance.safetensors holds the trained tensors; the architecture loads them via the project's private engine.
Source du modèle
- Type
- Text model
- Taille du fichier
- 1,15 GB
- Modèle de base
- Anima
- Version
- vresonance
- Mis à jour
- 3 oct. 2026
- Éditeur
- @FatStinkyPanda
- Téléchargements
- 8
- Tâches
- Audio
- Source
- Hugging Face
Description de la source
FatStinkyPanda · Resonance — step 38,000
A from-scratch neural text-to-speech engine (SNAC 24 kHz codec), trained in the Anima project (https://github.com/FatStinkyPanda/Anima). The published resonance.safetensors holds the trained tensors; the architecture loads them via the project's private engine.
Proprietary architecture. The architecture and training innovations are NOT public. This repo hosts the trained weights + tokenizer only; the config + modeling code stay private. Benchmarks run on neutral free compute and are published openly so the numbers are verifiable without exposing how the model works.
Latest held-out benchmarks (neutral compute)
- behavior: 1.0
- layer_health: 1.0
- stability: 1.0
- coarse_accuracy: 0.0618
- overall: 0.6506
- tf_coarse_accuracy: 0.0618
- tf_loss: 22.0305
- tf_loss_coarse: 8.1523
Created & released by FatStinkyPanda. For access or collaboration, contact the creator.
Sources
1 source
Sources
1 sourceVérifié 3 oct.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactExtraits de sources
3 extraits
Extraits de sources
3 extraits--- license: other tags: [resonance, anima, tts, speech, from-scratch] --- # FatStinkyPanda · Resonance — step 38,000 A from-scratch **neural text-to-speech** engine (SNAC 24 kHz codec), trained in the **Anima** project (https://github.com/FatStinkyPanda/Anima). The published `resonance.safetensors` holds the trained tensors; the architecture loads them via the project's private engine. > **Proprietary architecture.** The architecture and training innovations are NOT public. This repo hosts the trained **weights + tokenizer only**; the config + modeling code stay private. Benchmarks run on **neutral free compute** and are published openly so the numbers are verifiable without exposing how the model works. ## Latest held-out benchmarks (neutral compute) - **behavior**: 1.0 - **layer_health**: 1.0 - **stability**: 1.0 - **coarse_accuracy**: 0.0618 - **overall**: 0.6506 - **tf_coarse_accuracy**: 0.0618 - **tf_loss**: 22.0305 - **tf_loss_coarse**: 8.1523 Created & released by **FatStinkyPanda**. For access or collaboration, contact the creator.
Source context: 267 downloads · 0 likes · Repo FatStinkyPanda/resonance
Source context: 263 downloads · 0 likes · Repo FatStinkyPanda/resonance
