Saltar al contenido
ModelPublicadoExterno
Descargar

Model At CheckPoint 20000

This is a fully independent, merged deployment of the VibeVoice acoustic model fine-tuned for Egyptian Arabic at checkpoint 20000. It includes the integrated Qwen tokenizer configs and base weights side-by-side.

Fuentehuggingface.co/MohammedEhab20/Model-At-checkPoint-20000/tree/121e7f1a92cd97a7a49e78c55ee84b5496f09f51
TipoText modelVersiónmodelCcalidad

Fuente del modelo

Tipo
Text model
Tamaño del archivo
5,04 GB
Versión
vmodel
Actualizado
26 sept 2026
Descargas
2
Fuente
Hugging Face

Descripción de la fuente

Model-At-checkPoint-20000

This is a fully independent, merged deployment of the VibeVoice acoustic model fine-tuned for Egyptian Arabic at checkpoint 20000. It includes the integrated Qwen tokenizer configs and base weights side-by-side.

📦 Repository Structure

  • model.safetensors: Independent merged model weights.
  • voices/: Reference speech audio samples.
  • Tokenizer and configuration JSON files.

🚀 How to Use (Inference API / Colab)

import torch
from peft import PeftModel
# Load this repository directly using standard HuggingFace or VibeVoice modules:
# model = VibeVoiceForConditionalGeneration.from_pretrained("MohammedEhab20/Model-At-checkPoint-20000", trust_remote_code=True)

🎛️ Runtime Parameters (CFG Scale)

The Classifier-Free Guidance (CFG) scale is a runtime parameter and not baked into these weights. You can dynamically adjust it during inference calls:

  • Higher CFG (e.g., 5.0): Strict alignment with the prompt.
  • Lower CFG (e.g., 3.5): More natural flow and creativity.

Fuentes

1 fuente
Hugging FacePrincipalVersión 121e7f1a92cd97a7a49e78c55ee84b5496f09f51
huggingface.co/MohammedEhab20/Model-At-checkPoint-20000/tree/121e7f1a92cd97a7a49e78c55ee84b5496f09f51

Verificado 29 ago

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 5,04 GB · SHA-256 043c20141b69…56dd · Hugging Face

Download file

Extractos de fuentes

2 extractos
Readme29 agohuggingface.co/MohammedEhab20/Model-At-checkPoint-20000

--- license: apache-2.0 language: - ar tags: - text-to-speech - tts - acoustic-model - vibevoice --- # Model-At-checkPoint-20000 This is a fully independent, merged deployment of the VibeVoice acoustic model fine-tuned for Egyptian Arabic at checkpoint 20000. It includes the integrated Qwen tokenizer configs and base weights side-by-side. ## 📦 Repository Structure * `model.safetensors`: Independent merged model weights. * `voices/`: Reference speech audio samples. * Tokenizer and configuration JSON files. ## 🚀 How to Use (Inference API / Colab) ```python import torch from peft import PeftModel # Load this repository directly using standard HuggingFace or VibeVoice modules: # model = VibeVoiceForConditionalGeneration.from_pretrained("MohammedEhab20/Model-At-checkPoint-20000", trust_remote_code=True) ``` ## 🎛️ Runtime Parameters (CFG Scale) The Classifier-Free Guidance (CFG) scale is a runtime parameter and **not baked into these weights**. You can dynamically adjust it during inference calls: * Higher CFG (e.g., `5.0`): Strict alignment with the prompt. * Lower CFG (e.g., `3.5`): More natural flow and creativity.

Note29 agohuggingface.co/MohammedEhab20/Model-At-checkPoint-20000

Source context: 2 downloads · 0 likes · Pipeline text-to-speech · Library vibevoice · Repo MohammedEhab20/Model-At-checkPoint-20000