Downloads · 30 days
5
1% of all-time downloads
tts_prodiff_eng_mspk
Fhrozen/tts_prodiff_eng_mspk
tts_prodiff_eng_mspk is a text-to-speech model from Fhrozen. Use it when you need text read aloud. It is set up for espnet. The card lists the license as cc-by-4.0.
All-time downloads
955
Public
Repo size
116 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth114 MB · 98%
At a glance
- Task
- Text-to-Speech
- Library
- espnet
- License
- cc-by-4.0
- Access
- Public
- Created
- Jan 16, 2023
- Updated
- Apr 6, 2023
- SHA
- 55118f3e
Datasets
Model card
From the Hugging Face model README
TTS model - ProDiff with GST + X-Vector
No support given.
Details
num_iters_per_epoch: 250
max_epoch: 800
batch_bins: 8000000
tts_conf:
spk_embed_dim: 192
- Task
- Text-to-Speech
- Library
- espnet
- License
- cc-by-4.0
- Languages
- en
- Created
- Jan 16, 2023
- Updated
- Apr 6, 2023