How to use microsoft/VibeVoice-ASR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="microsoft/VibeVoice-ASR")
# Load model directly from transformers import VibeVoiceForASRTraining model = VibeVoiceForASRTraining.from_pretrained("microsoft/VibeVoice-ASR", dtype="auto")
I love the idea of Hotwords, but I’m struggling to find a guide on how to actually add them. Is the process identical to using the Whisper 'initial prompt' field, or is there a different method I should be using?
· Sign up or log in to comment
