Text-to-Speech
Transformers
Safetensors
MLX
English
vibevoice_streaming
Realtime TTS
Streaming text input
Long-form speech generation
6-bit
Instructions to use mlx-community/VibeVoice-Realtime-0.5B-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlx-community/VibeVoice-Realtime-0.5B-6bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="mlx-community/VibeVoice-Realtime-0.5B-6bit")# Load model directly from transformers import VibeVoiceStreamingForConditionalGenerationInference model = VibeVoiceStreamingForConditionalGenerationInference.from_pretrained("mlx-community/VibeVoice-Realtime-0.5B-6bit", device_map="auto") - MLX
How to use mlx-community/VibeVoice-Realtime-0.5B-6bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir VibeVoice-Realtime-0.5B-6bit mlx-community/VibeVoice-Realtime-0.5B-6bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
File size: 360 Bytes
230f47a | 1 2 3 4 5 6 7 8 9 10 11 12 13 | {
"processor_class": "VibeVoiceStreamingProcessor",
"speech_tok_compress_ratio": 3200,
"db_normalize": true,
"audio_processor": {
"feature_extractor_type": "VibeVoiceTokenizerProcessor",
"sampling_rate": 24000,
"normalize_audio": true,
"target_dB_FS": -25,
"eps": 1e-06
},
"language_model_pretrained_name": "Qwen/Qwen2.5-0.5B"
} |