How to use Fhrozen/tts_prodiff_jp_multispk with ESPnet:
from espnet2.bin.tts_inference import Text2Speech model = Text2Speech.from_pretrained("Fhrozen/tts_prodiff_jp_multispk") speech, *_ = model("text to generate speech from")
No support given.
num_iters_per_epoch: 250 max_epoch: 600 batch_bins: 6000000 tts_conf: spk_embed_dim: 192
