Umberto Cappellazzo

icon company University of Trento/Fondazione Bruno Kessler icon location Trento icon location PhD candidate @ University of Trento. Interests: Continual Learning and efficient finetuning for speech, multimodal LLMs.

Results 16 comments of Umberto Cappellazzo

Issues when I try to run the yesno recipe for testing purposes

I opted for conda installation since in the official documentation it's recommended that we install k2 using conda

Issues when I try to run the yesno recipe for testing purposes

In the end I managed to install it via pip. However, I would recommend that you update the installation instructions, at least put the "recommended" to the pip installation rather...

Issues when I try to run the yesno recipe for testing purposes

After carrying out data preparation for LibriSpeech (it is successful), I'm trying to run the training stage for conformer_ctc2 (./conformer_ctc/train.py --full-libri False --num-epochs 30), but I get this error: ```...

Issues when I try to run the yesno recipe for testing purposes

My colleague and I tried to start from a new pytorch docker image and installed all the dependencies again, and it does work. Probably some days ago we had some...

Issues when I try to run the yesno recipe for testing purposes

Hi, I ran the conformer_ctc recipe with the following command: ``` ./conformer_ctc/train.py --full-libri False --num-epochs 30 ``` and the training was ok and also the decoding step was ok. With...

Issues when I try to run the yesno recipe for testing purposes

In order to run "pure-ctc" training, both --num-encoder-layers and --att-rate **MUST** be set to 0 and 0. , respectively. Only setting --num-encoder-layers 0 results in the error I attached above.