Downloads · 30 days
324
13% of all-time downloads
GLaDOS_TTS
DavesArmoury/GLaDOS_TTS
GLaDOS_TTS is a text-to-speech model from DavesArmoury. Use it when you need text read aloud. It is set up for nemo. The card lists the license as cc-by-4.0.
This was trained with the ipython notebok HERE
All-time downloads
2.5K
Public
Repo size
736 MB
Likes
12
Public
Repo makeup
Click a slice to open those files.
.nemo526 MB · 71%
At a glance
- Task
- Text-to-Speech
- Library
- nemo
- License
- cc-by-4.0
- Access
- Public
- Created
- Feb 20, 2024
- Updated
- Sep 11, 2024
- SHA
- b64622ad
Model card
From the Hugging Face model README
GLaDOS
Training
This was trained with the ipython notebok HERE
RIVA
Look here https://docs.nvidia.com/deeplearning/riva/user-guide/docs/quick-start-guide.html
On Local Machine
pip3 install whl
pip3 install nemo2riva
nemo2riva --out hifigan.riva hifigan.nemo --key None
nemo2riva --out fastpitch.riva fastpitch.nemo --key None
scp .riva files to jetson under ~/RIVA/artifacts
On Jetson
docker run --gpus all -it --rm \
-v /home/davesarmoury/RIVA/artifacts:/servicemaker-dev \
-v /home/davesarmoury/RIVA/riva_repo:/data \
--entrypoint="/bin/bash" \
nvcr.io/nvidia/riva/riva-speech:2.13.1-servicemaker-l4t-aarch64
riva-build speech_synthesis \
/servicemaker-dev/glados.rmir:tlt_encode \
/servicemaker-dev/glados_fastpitch.riva:tlt_encode \
/servicemaker-dev/glados_hifigan.riva:tlt_encode \
--voice_name=GLaDOS \
--sample_rate 22050
riva-deploy /servicemaker-dev/glados.rmir:tlt_encode /data/models
# Exit docker
ngc registry resource download-version nvidia/riva/riva_quickstart_arm64:2.13.1
cd riva_quickstart_arm64_v2.13.1
bash riva_init.sh
copy glados.riva files into riva models dir
riva_start.sh
- Task
- Text-to-Speech
- Library
- nemo
- License
- cc-by-4.0
- Languages
- en
- Created
- Feb 20, 2024
- Updated
- Sep 11, 2024