Instructions to use aoi-ot/VibeVoice-Large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VibeVoice
How to use aoi-ot/VibeVoice-Large 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("aoi-ot/VibeVoice-Large") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "aoi-ot/VibeVoice-Large", 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
Not all heros wear capes
#1
by iluvecats11 - opened
weird to see microsoft randomly try nuke their own model
https://archive.softwareheritage.org/browse/origin/directory/?origin_url=https://github.com/microsoft/VibeVoice github
weird to see microsoft randomly try nuke their own model
Not weird at all alpindale/WizardLM-2-8x22B
ikr!!