cybercoder
cybercoder
To preprocess the data for training or prediction use: ` def prepare_input(self, input_sent):` If you want information about each input max length, check following code part (each model version tried...
Great suggestion, if you can create pull request with this update will accept it
@MoeNeuron I started to prepare the pip publish in the following branch: https://github.com/Barqawiz/Shakkala/tree/prepare-pip-install but something does not connect after the publish, lets meet based on your availability to validate.
The issue is resolved and shakkala is publish. pip install shakkala==1.6 For more details: https://pypi.org/project/shakkala/1.6/ Thanks for the suggestion.
Unfortunately, I cannot export a new one as the data is old, but I can explain the layers. - bi-directional RRN. - batch normalisation. - bi-directional RRN. - fully dense...
I am glad you liked the shakkala project; what is the issue with the cpu setup? It should work typically. Did you phase specific errors?
The API key feature is still not accessible for the public.
If the module available in hugging face, we can update or validate the hugging face wrapper to use the SeamlessM4T.
I am going to create a new project item to address your first point to support streaming. The second point. it is not clear but please open another issue for...
Openai backend does not support the session id, but you can send the messages history as part of the call. This way the model will be aware of the ongoing...