Akhil Tolani

Training medium/large complexity models on 4xA100 80GB GPUs

4

Hi, I'm currently retraining MusicGen with 200k audio files. I have access to 4xA100 80GB GPUs, which is enough to train a 420.37M param model (small config) out of the...

CE/PPL values of the default MusicGen small/medium/large models

2

Hi! I've been retraining MusicGen with a custom dataset of 200,000 audio files (15,000 hours of music) and I wanted to know whats the CE/PPL values of the model trained...

Training on single GPU works but Multiple GPUs throws an error

2

I have a lambda blade setup with 8x Nvidia Titan RTX GPUs. Command for single GPU training - `dora run solver=compression/debug` Output - Works ✅ ``` Dora directory: /home/jovyan/data/rDataset/audiocraft/output_jovyan [09-13...

Could this theoretically be retrained from scratch to generate singing vocals?

4

Given a 10k hour dataset of singing vocals (_instead of the current audiobook reading content_), could this model be ported to be able to sing/generate vocals?

Marketplace listings failing

1

Creating listings seems to be randomly failing since the past few days https://polygonscan.com/address/0x66592ad3fbd87b8631e40143b2f6671a9dd73283 Any ideas what could be causing this issue? I can see the "value" column randomly switched from...