ModelPrésentéExterne

Supertonic

100% PyTorch weights for Supertonic-3, reconstructed bit-exact from the ONNX release (corr 1.0). Use with code: github.com/yentur/supertonic-v3-pytorch.

Sourcehuggingface.co/omeryentur/supertonic/tree/e61deee5c8db08f37585ce71a78577484ab3a62c

TypeOtherVersionRevision e61deeeCClasse

Source du modèle

Type: Other
Taille du fichier: 101 KB–244 MB
Version: vRevision e61deee
Mis à jour: 25 sept. 2026
Téléchargements: 0
Source: Hugging Face

Description de la source

Supertonic v3 — PyTorch weights

100% PyTorch weights for Supertonic-3, reconstructed bit-exact from the ONNX release (corr 1.0). Use with code: github.com/yentur/supertonic-v3-pytorch.

Files: *.safetensors (the 4 modules + cfg tokens) + assets/ (unicode_indexer, tts.json, voice_styles).

from supertonic_v3 import SupertonicV3
m=SupertonicV3("WEIGHTS","assets"); wav,sr=m.synth("merhaba ben freya nasılsınız.","F1")

Original model © Supertone Inc (OpenRAIL).

Sources

1 source

Hugging FacePrincipalVersion e61deee5c8db08f37585ce71a78577484ab3a62c

huggingface.co/omeryentur/supertonic/tree/e61deee5c8db08f37585ce71a78577484ab3a62c

Vérifié 6 sept.

Download files

Artefacts du modèle

5 artefacts

cfg_tokens.safetensors

safetensors · 101 KB · SHA-256 60efded59bf2…ae55 · Hugging Face

Download file

duration_predictor.safetensors

safetensors · 3,31 MB · SHA-256 8c33afe3a9be…53bb · Hugging Face

Download file

text_encoder.safetensors

safetensors · 34,4 MB · SHA-256 8f84040f4f76…9fb8 · Hugging Face

Download file

vector_estimator.safetensors

safetensors · 244 MB · SHA-256 6d8f820d5a6e…d5f9 · Hugging Face

Download file

vocoder.safetensors

safetensors · 96,7 MB · SHA-256 ff5b1404ce33…c357 · Hugging Face

Download file

Extraits de sources

2 extraits

Readme6 sept.huggingface.co/omeryentur/supertonic

--- license: openrail language: [tr, en] pipeline_tag: text-to-speech tags: [text-to-speech, tts, supertonic, pytorch, turkish] --- # Supertonic v3 — PyTorch weights 100% PyTorch weights for [Supertonic-3](https://huggingface.co/Supertone/supertonic-3), reconstructed bit-exact from the ONNX release (corr 1.0). Use with code: **github.com/yentur/supertonic-v3-pytorch**. Files: `*.safetensors` (the 4 modules + cfg tokens) + `assets/` (unicode_indexer, tts.json, voice_styles). ```python from supertonic_v3 import SupertonicV3 m=SupertonicV3("WEIGHTS","assets"); wav,sr=m.synth("merhaba ben freya nasılsınız.","F1") ``` Original model © Supertone Inc (OpenRAIL).

Note6 sept.huggingface.co/omeryentur/supertonic

Source context: 0 downloads · 1 likes · Pipeline text-to-speech · Library supertonic · Repo omeryentur/supertonic