Instructions to use iamvaar/vibevoice-realtime-0.5b-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VibeVoice
How to use iamvaar/vibevoice-realtime-0.5b-onnx with VibeVoice:
import torch, soundfile as sf, librosa, numpy as np from vibevoice.processor.vibevoice_processor import VibeVoiceProcessor from vibevoice.modular.modeling_vibevoice_inference import VibeVoiceForConditionalGenerationInference # Load voice sample (should be 24kHz mono) voice, sr = sf.read("path/to/voice_sample.wav") if voice.ndim > 1: voice = voice.mean(axis=1) if sr != 24000: voice = librosa.resample(voice, sr, 24000) processor = VibeVoiceProcessor.from_pretrained("iamvaar/vibevoice-realtime-0.5b-onnx") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "iamvaar/vibevoice-realtime-0.5b-onnx", torch_dtype=torch.bfloat16 ).to("cuda").eval() model.set_ddpm_inference_steps(5) inputs = processor(text=["Speaker 0: Hello!\nSpeaker 1: Hi there!"], voice_samples=[[voice]], return_tensors="pt") audio = model.generate(**inputs, cfg_scale=1.3, tokenizer=processor.tokenizer).speech_outputs[0] sf.write("output.wav", audio.cpu().numpy().squeeze(), 24000) - Notebooks
- Google Colab
- Kaggle
Download language_model.onnx.data from iamvaar/vibevoice-realtime-0.5b-onnx: direct link, hf CLI and curl.
- Browser
- Download file 239 MB
-
https://huggingface.co/iamvaar/vibevoice-realtime-0.5b-onnx/resolve/main/language_model.onnx.data
- Command line
-
hf download hf://iamvaar/vibevoice-realtime-0.5b-onnx/language_model.onnx.data
-
curl -L -o language_model.onnx.data https://huggingface.co/iamvaar/vibevoice-realtime-0.5b-onnx/resolve/main/language_model.onnx.data
239 MB
- Xet hash:
- 19dc69e37ec0d7fd450a58eaeab8e7c0429e4a639d0ea2e24c0078f09f619b70
- Size of remote file:
- 239 MB
- SHA256:
- 286ef4fe0a70c3388a35c2bf1cf96491a0ad9c24a80718f4a80eb190ea4291a4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.