How to use lemuriandezapada/VibeVoice-Embed with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="lemuriandezapada/VibeVoice-Embed", trust_remote_code=True)
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("lemuriandezapada/VibeVoice-Embed", trust_remote_code=True, device_map="auto")
How to use lemuriandezapada/VibeVoice-Embed 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("lemuriandezapada/VibeVoice-Embed") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "lemuriandezapada/VibeVoice-Embed", 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)
