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")
c418ba2
1
2
3
4
5
{ "<ctc_blank>": 80, "<mask>": 79 }
Create images in seconds. No sign-up, no paywall, no setup.
