Text-to-Speech
Transformers
Safetensors
MLX
English
vibevoice_streaming
Realtime TTS
Streaming text input
Long-form speech generation
4-bit precision
Instructions to use theoracleguy/VibeVoice-Realtime-0.5B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use theoracleguy/VibeVoice-Realtime-0.5B-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="theoracleguy/VibeVoice-Realtime-0.5B-4bit")# Load model directly from transformers import VibeVoiceStreamingForConditionalGenerationInference model = VibeVoiceStreamingForConditionalGenerationInference.from_pretrained("theoracleguy/VibeVoice-Realtime-0.5B-4bit", device_map="auto") - MLX
How to use theoracleguy/VibeVoice-Realtime-0.5B-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir VibeVoice-Realtime-0.5B-4bit theoracleguy/VibeVoice-Realtime-0.5B-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
mlx-community/VibeVoice-Realtime-0.5B-4bit
This model was converted to MLX format from microsoft/VibeVoice-Realtime-0.5B using mlx-audio version 0.2.6.
Refer to the original model card for more details on the model.
Use with mlx
pip install -U mlx-audio
python -m mlx_audio.tts.generate --model mlx-community/VibeVoice-Realtime-0.5B-4bit --text "Hello, this is VibeVoice real-time 0.5B model." --voice en-Emma_woman
- Downloads last month
- -
Model size
1B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for theoracleguy/VibeVoice-Realtime-0.5B-4bit
Base model
Qwen/Qwen2.5-0.5B