Instructions to use mlboydaisuke/VibeVoice-Realtime-0.5B-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use mlboydaisuke/VibeVoice-Realtime-0.5B-LiteRT with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- VibeVoice
How to use mlboydaisuke/VibeVoice-Realtime-0.5B-LiteRT 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("mlboydaisuke/VibeVoice-Realtime-0.5B-LiteRT") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "mlboydaisuke/VibeVoice-Realtime-0.5B-LiteRT", 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
Link the card back to its collection and the request box
Browse files
README.md
CHANGED
|
@@ -109,3 +109,11 @@ val hidden = outputs[0].readFloat() // [1,1,896]
|
|
| 109 |
make a short sentence take ~30 s on a Pixel 8a. See the conversion notes for the ML Drift decoder bug.
|
| 110 |
|
| 111 |
Original model: [microsoft/VibeVoice-Realtime-0.5B](https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B) (MIT).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
make a short sentence take ~30 s on a Pixel 8a. See the conversion notes for the ML Drift decoder bug.
|
| 110 |
|
| 111 |
Original model: [microsoft/VibeVoice-Realtime-0.5B](https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B) (MIT).
|
| 112 |
+
|
| 113 |
+
<!-- funnel:v1 -->
|
| 114 |
+
|
| 115 |
+
---
|
| 116 |
+
|
| 117 |
+
**Want a different model on-device?** [Open a request](https://github.com/john-rocky/on-device-requests) — free, open weights only; the export and its measured numbers get published publicly.
|
| 118 |
+
|
| 119 |
+
<!-- /funnel:v1 -->
|