Instructions to use STCOMP/vibevoice-majel-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VibeVoice
How to use STCOMP/vibevoice-majel-lora 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("STCOMP/vibevoice-majel-lora") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "STCOMP/vibevoice-majel-lora", 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 diffusion_head_full.bin from STCOMP/vibevoice-majel-lora: direct link, hf CLI and curl.
- Browser
- Download file 1.34 GB
-
https://huggingface.co/STCOMP/vibevoice-majel-lora/resolve/main/diffusion_head_full.bin
- Command line
-
hf download hf://STCOMP/vibevoice-majel-lora/diffusion_head_full.bin
-
curl -L -o diffusion_head_full.bin https://huggingface.co/STCOMP/vibevoice-majel-lora/resolve/main/diffusion_head_full.bin
1.34 GB
- Xet hash:
- 8995492b34b773da8157704b04ce422aa26ce62b2d56680ec63c9770ae024d40
- Size of remote file:
- 1.34 GB
- SHA256:
- 772a7dc550708324ccc2a80745c685d44d679ea2a1a8bb68e0f67e5c36c7eccc
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.