guillaume-be

> > Could you please clarify if by language agnostic you mean independent of the language (e.g. English, French, Spanish...) or independent of the target language (e.g. Python, Rust,...)? >...

Hi @genderev , For an overview of the pre-and post-processing steps, I would recommend having a look at the Transformers' library (implemented in Python). You will find implementation for end-to-end...

Hello @remotejob , The generic functionality offered by `EncoderDecoderModel`, allowing to pass an arbitrary encoder and decoder is not yet supported in the Rust library. The base concept it relies...

Hello @LambdaMan2K , You are right - there are currently no speech to text models implemented. The models could take tensors as an input but the loading and pre-processing of...

Hi @QuantumEntangledAndy , Thank you for raising this behaviour: I have noticed the same while troubleshooting the other issue. I tried to run a dialogue with the Python's Transformers implementation...

Hi @SFosterQRA , You are correct that there are no pretrained models supporting chunking or sentence detection yet. To my knowledge, there are no transformer-based architecture in Hugging face's model...

Hello @Raduc4 , The current released version (1.18) requires libtorch v1.11. If pulling the code directly from this repository libtorch 1.12 is required (this is because of the different dependencies...

Hello @Raduc4 , These errors are caused because the `tch` dependency fails to link the libtorch installation. I am not able to reproduce the error, maybe you will be able...

Hello @vimal-quilt , The conversion utilities print the converted tensors and their path as a result of the conversion. Could you please double check if the tensor was exported with...

Fixed by https://github.com/guillaume-be/rust-bert/pull/296