Text-to-Speech
Transformers
Safetensors
VibeVoice
English
Chinese
tts
speech-synthesis
bitsandbytes
4bit
quantized
4-bit precision
Instructions to use marksverdhai/vibevoice-7b-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use marksverdhai/vibevoice-7b-bnb-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="marksverdhai/vibevoice-7b-bnb-4bit")# Load model directly from transformers import VibeVoiceForConditionalGenerationInference model = VibeVoiceForConditionalGenerationInference.from_pretrained("marksverdhai/vibevoice-7b-bnb-4bit", dtype="auto") - VibeVoice
How to use marksverdhai/vibevoice-7b-bnb-4bit 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("marksverdhai/vibevoice-7b-bnb-4bit") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "marksverdhai/vibevoice-7b-bnb-4bit", 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
- Xet hash:
- d0965a95d8cc54511dfb6672b585212a65f14e2b872cc5c8515a4a416d5b1d7a
- Size of remote file:
- 4.95 GB
- SHA256:
- bb5b251fc215bcd5ee9d74bc4383aece74ab8a4e38d402017bcf349c20cc02a6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.