How to use microsoft/speecht5_vc with Transformers:
# Load model directly from transformers import AutoProcessor, SpeechT5ForSpeechToSpeech processor = AutoProcessor.from_pretrained("microsoft/speecht5_vc") model = SpeechT5ForSpeechToSpeech.from_pretrained("microsoft/speecht5_vc")
This model is very impressive. I would like to know how the 512-dimensional x-vector is extracted from the wave file here. Thank you!
· Sign up or log in to comment
