Instructions to use Rcarvalo/vibevoice with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VibeVoice
How to use Rcarvalo/vibevoice 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("Rcarvalo/vibevoice") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "Rcarvalo/vibevoice", 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
| { | |
| "processor_class": "VibeVoiceStreamingProcessor", | |
| "speech_tok_compress_ratio": 3200, | |
| "db_normalize": true, | |
| "audio_processor": { | |
| "feature_extractor_type": "VibeVoiceTokenizerProcessor", | |
| "sampling_rate": 24000, | |
| "normalize_audio": true, | |
| "target_dB_FS": -25, | |
| "eps": 1e-06 | |
| }, | |
| "language_model_pretrained_name": "Qwen/Qwen2.5-0.5B" | |
| } |