Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
espnet
/
kan-bayashi_jsut_tts_train_conformer_fastspeech2_tacotron2_teacher_raw-truncated-569e81
like
0
Text-to-Speech
ESPnet
jsut
Japanese
audio
arxiv:
1804.00015
License:
cc-by-4.0
Model card
Files
Files and versions
Community
Use this model
ddc98ec
kan-bayashi_jsut_tts_train_conformer_fastspeech2_tacotron2_teacher_raw-truncated-569e81
/
exp
/
tts_train_conformer_fastspeech2_tacotron2_teacher_raw_phn_jaconv_pyopenjtalk_prosody
1 contributor
History:
1 commit
Siddhant
import from zenodo
ddc98ec
almost 3 years ago
images
import from zenodo
almost 3 years ago
config.yaml
6 kB
import from zenodo
almost 3 years ago
train.loss.ave_5best.pth
282 MB
LFS
import from zenodo
almost 3 years ago