Instructions to use mudler/vibevoice.cpp-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VibeVoice
How to use mudler/vibevoice.cpp-models 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("mudler/vibevoice.cpp-models") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "mudler/vibevoice.cpp-models", 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
add Q4_K (matmul) - 9.7 GB, -70%
Browse files- .gitattributes +1 -0
- vibevoice-asr-q4_k.gguf +3 -0
.gitattributes
CHANGED
|
@@ -38,3 +38,4 @@ voice-en-Emma.gguf filter=lfs diff=lfs merge=lfs -text
|
|
| 38 |
voice-en-Carter_man.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
vibevoice-realtime-0.5B-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
vibevoice-asr-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 38 |
voice-en-Carter_man.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
vibevoice-realtime-0.5B-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
vibevoice-asr-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
vibevoice-asr-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
|
vibevoice-asr-q4_k.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4eee48b9d0d42f71b773b804aa6728c99971c38d54f3c86cf1fd0fc1fc49a9ad
|
| 3 |
+
size 10392063296
|