# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("forkjoin-ai/vibevoice-1.5b", device_map="auto")Quick Links
Vibevoice 1.5B (SafeTensors)
SafeTensors mirror of VibeVoice/VibeVoice-1.5B for distributed edge inference — powered by the Aether runtime on Edgework.ai.
Model Details
| Property | Value |
|---|---|
| Base model | VibeVoice/VibeVoice-1.5B |
| Format | SafeTensors |
| Weight files | 3 shard(s) *.safetensors |
| License | apache-2.0 |
Usage
These are SafeTensors weights — load them with the model's native framework (e.g. transformers / diffusers), not llama.cpp.
huggingface-cli download forkjoin-ai/vibevoice-1.5b --local-dir ./vibevoice-1.5b
About
Published by AFFECTIVELY · Managed by @buley. Mirrored for distributed edge inference via the Aether runtime.
- Downloads last month
- 9
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="forkjoin-ai/vibevoice-1.5b")