cvillela

(Wikihow-T5) Not seeing any ROUGE Score improvement in training

1

Hello! I am using the wikihow-fine-tuning-T5 script (unchanged, except I'm using tyhe XSUM dataset) for some research, but I'm having trouble training the model. Although the dataset steps seem to...

Fewer than expected results were retrieved when querying for len(index) items

2

This is a noted issue already, but I am opening another card for visibility as the previous one has been open for over 4 months! My objective would be to...

Producing audio in different Sample Rate

3

Hey! I was wondering if it was possible to train the model in 48kHz audio, and then generate audio directly in 48kHz. Has anyone attempted this?

[REQUEST]: Single Device Multi-Channel Selection as Output

1

### In a few words, describe your idea I would like to be able to output the voices to a single device, selecting which channel I wanted to output each...

Finetuning on own data

3

Hello again @fschmid56 , thanks for the awesome repo! I would like to finetune DyMNs on my own dataset for audio classification. Is it possible? If so, would the best...