How to use sapinsapin/speecht5_vc-pld with Transformers:
# Load model directly from transformers import AutoProcessor, SpeechT5ForSpeechToSpeechWithLoss processor = AutoProcessor.from_pretrained("sapinsapin/speecht5_vc-pld") model = SpeechT5ForSpeechToSpeechWithLoss.from_pretrained("sapinsapin/speecht5_vc-pld", device_map="auto")
