Automatic Speech Recognition
Transformers
Safetensors
VibeVoice
ASR
Transcription
Speech-to-Text
Streaming
Instructions to use microsoft/VibeVoice-ASR-Streaming-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/VibeVoice-ASR-Streaming-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="microsoft/VibeVoice-ASR-Streaming-7B")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, VibeVoiceForASRStreamingTraining processor = AutoProcessor.from_pretrained("microsoft/VibeVoice-ASR-Streaming-7B") model = VibeVoiceForASRStreamingTraining.from_pretrained("microsoft/VibeVoice-ASR-Streaming-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
timestamp needed
#1
by 999DavidYang999 - opened
thanks for the good jobs of microsoft.
but i have question: how can i get timestamp by using vibevoice-asr-streaming?
I found timestamp output in the demo page, but i can not optain it through the function. so i think it will be useful and helpful if the official can has a standard suppter.