Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature/split arch #146

Open
wants to merge 54 commits into
base: main
Choose a base branch
from
Open

Feature/split arch #146

wants to merge 54 commits into from

Conversation

kristiankielhofner
Copy link
Contributor

No description provided.

Add users like so (using bcrypt):

./utils.sh htpasswd -B /nginx/htpasswd my_user
This ensures we don't use potentially insecure openssl from host

Additionally, it sets proper permissions for key files on host
- Build our own nginx container to include htpasswd so permissions are set
- Wrap all openssl and related commands to WIS nginx docker container
Before:
3067.8740000000003 small/2

After:
2094.071 small/2

- Build with clang 16
- Bump oneDNN (with faster int8)
- Bump oneAPI
- TensorRT 23.05
- oneAPI 2023.1.0
- oneDNN 3.1.1
- clang 14

Also include ctranslate2 fork with whisper-distil support and transformers 4.35.0
Pin FROM docker container
Set enable_text_splitting = True
Add hu and ko, change chinese to zh
Limit range of top_p based on model specs
Update comments
curl -F '[email protected]' \
  'https://wis:19000/api/tts?speaker=your_speaker_name'

Then you can immediately pass speaker=your_speaker_name to GET
Rename speecht5 to CLB
ctranslate2 now natively supports CUDA 12

Warning: this breaks custom_settings.py due to pydantic changes
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant