Downloads · 30 days
10
3% of all-time downloads
vits-commonvoice9.0
z-uo/vits-commonvoice9.0
vits-commonvoice9.0 is a text-to-speech model from z-uo. Use it when you need text read aloud. It is set up for transformers.
Train on Mozzila Common voice v9.0 it with Coqui VITS
All-time downloads
346
Public
Repo size
6.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth7.3 GB · 99%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- Access
- Public
- Created
- Jun 12, 2022
- Updated
- Jun 12, 2022
- SHA
- 5f8da2bc
Model card
From the Hugging Face model README
Common Voice it Vits
Train on Mozzila Common voice v9.0 it with Coqui VITS
# Coqui tts sha commit coquitts: 0cf3265a4686d7e856bd472cdaf1572d61cab2b8
PYTORCH_CUDA_ALLOC_CONF="max_split_size_mb:25" CUDA_VISIBLE_DEVICES=1 python recipes/common_voice/vits/train_vits.py
CUDA_VISIBLE_DEVICES=0 tts-server --model_path "/run/media/opensuse/Barracuda/Models/TTS_new/trained_common_voice/vits_vctk-June-05-2022_03+45PM-0cf3265a/best_model.pth" --config_path "/run/media/opensuse/Barracuda/Models/TTS_new/trained_common_voice/vits_vctk-June-05-2022_03+45PM-0cf3265a/config.json"
- Task
- Text-to-Speech
- Library
- transformers
- Languages
- it
- Created
- Jun 12, 2022
- Updated
- Jun 12, 2022