Instructions to use vibevoice/VibeVoice-1.5B-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vibevoice/VibeVoice-1.5B-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="vibevoice/VibeVoice-1.5B-hf")# Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("vibevoice/VibeVoice-1.5B-hf") model = AutoModelForTextToWaveform.from_pretrained("vibevoice/VibeVoice-1.5B-hf", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from vibevoice/VibeVoice-1.5B-hf: direct link, hf CLI and curl.
- Browser
- Download file 511 Bytes
-
https://huggingface.co/vibevoice/VibeVoice-1.5B-hf/resolve/main/processor_config.json
- Command line
-
hf download hf://vibevoice/VibeVoice-1.5B-hf/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/vibevoice/VibeVoice-1.5B-hf/resolve/main/processor_config.json
511 Bytes
| { | |
| "audio_bos_token": "<|vision_start|>", | |
| "audio_eos_token": "<|vision_end|>", | |
| "audio_token": "<|vision_pad|>", | |
| "feature_extractor": { | |
| "eps": 1e-06, | |
| "feature_extractor_type": "VibeVoiceAcousticTokenizerFeatureExtractor", | |
| "feature_size": 1, | |
| "normalize_audio": true, | |
| "pad_to_multiple_of": 3200, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 24000, | |
| "target_dB_FS": -25 | |
| }, | |
| "processor_class": "VibeVoiceProcessor" | |
| } | |