Downloads · 30 days
173
7% of all-time downloads
hifigan-lj-v1
jaketae/hifigan-lj-v1
hifigan-lj-v1 is a text-to-speech model from jaketae. Use it when you need text read aloud. It is set up for transformers.
HiFi-GAN vocoder trained on the LJ Speech dataset. The modeling code is based on the official implementation and the fairseq adaptation.
All-time downloads
2.4K
Public
Repo size
112 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin55.8 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- Model type
- hifigan
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Feb 23, 2022
- SHA
- 85caaf4e
Datasets
Model card
From the Hugging Face model README
HiFi-GAN
HiFi-GAN vocoder trained on the LJ Speech dataset. The modeling code is based on the official implementation and the fairseq adaptation.
Usage
from transformers import AutoModel
model = AutoModel.from_pretrained("jaketae/hifigan-lj-v1", trust_remote_code=True)
- Task
- Text-to-Speech
- Library
- transformers
- Type
- hifigan
- Languages
- en
- Created
- Mar 2, 2022
- Updated
- Feb 23, 2022