philgzl
philgzl
### 🐛 Describe the bug Calling `torchaudio.load` with a file-like object as argument to load FLAC-encoded files sometimes returns incomplete tensors. It seems to happen with non-trivial tensors after a...
When using `pesq_batch` the user might be using batched audio waveforms that originally had different length and were padded to match their length before creating the batch. The padding however...
When trying to generate a music video using `examples/make_music_video.py` locally, I get the following error: ``` ╭───────────────────── Traceback (most recent call last) ──────────────────────╮ │ /zhome/d6/0/134239/stable-diffusion-videos/examples/make_music_video.py:49 │ │ in │ │...
This PR adds a script `scripts/make_video.py` to make videos from the command line, for those like me who prefer that over notebooks, to e.g. run from a cluster node. The...
Hi again, * Is the `state` argument of the different `foward` methods always `None` in your experiments? If not, when should it be set to something different from `None`? *...
Thanks for open sourcing this amazing work! I cannot seem to find what data was used to train the 48 kHz model (more specifically the HiFiGAN vocoder whose checkpoint I...
## What does this PR do? This PR adds a new metric [NISQA](https://github.com/gabrielmittag/NISQA) as suggested in #2464 Before submitting - [ ] Was this **discussed/agreed** via a Github issue? (no...
I am experiencing that in order to achieve HASPI scores that are not close to 1.0 for mild hearing losses, my signals must have a very low SNR. For example,...
Before submitting - [ ] Was this discussed/agreed via a Github issue? (no need for typos and docs improvements) - [ ] Did you read the [contributor guideline](https://github.com/Lightning-AI/lit-data/blob/main/CONTRIBUTING.md), Pull Request...
I would like to iterate over two `StreamingDataset` instances infinitely and yield new data derived from the output of both datasets. I am able to achieve this by wrapping two...