Text-to-Speech
Transformers
Safetensors
English
vibevoice_streaming
Realtime TTS
Streaming text input
Long-form speech generation
Instructions to use microsoft/VibeVoice-Realtime-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/VibeVoice-Realtime-0.5B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="microsoft/VibeVoice-Realtime-0.5B")# Load model directly from transformers import VibeVoiceStreamingForConditionalGenerationInference model = VibeVoiceStreamingForConditionalGenerationInference.from_pretrained("microsoft/VibeVoice-Realtime-0.5B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
finetune guide
#10
by devops724 - opened
Hi there
is there any guide how i can finetune this model for other languages ?
best regards
Here you go: https://github.com/vibevoice-community/VibeVoice/blob/main/FINETUNING.md#example-script
It's already done by community as far as I can see
This does not work with 0.5B model
https://github.com/microsoft/VibeVoice/issues/115 in this some comment are about asr & some are about 0.5b but still I am not able to get that can we write finetuning script or not for vibevoice-realtime-0.5b or not.
I think if github have complete architecture and weights then we can write also(finetuning script).