Andrei Andrusenko comments

Repositories
Issues
Comments

Results 3 comments of


                                            Andrei Andrusenko

Encoder-decoder attention extraction in ASR transcribe

Hi @mgaido91, You can find an example of this functionality in the streaming Canary decoding PR: [link](https://github.com/NVIDIA-NeMo/NeMo/pull/14765). We are using cross-attention outputs to guide the streaming decoding process for AlignAtt...

Will AlignAtt streaming for Canary model support beamsearch?

Hi @mjhanphd, You're right, the current AlignAtt implementation in NeMo only supports greedy Canary decoding. We have no plans to add beamsearch support in the near future. It would be...

Add support for streaming speech translation

Hi, could you add an example how to run the streaming speech translation to "Usage" field?