Piotr Żelasko
Piotr Żelasko
Dan's original comment: > I wonder if the next step could be creating an example setup for some dataset, e.g. mini_librispeech? > I'm thinking for now we can provide scripts...
We're currently running only unit tests, which prevent regressions to a limited extent. We could use a separate top-level test directory, e.g., `integration_tests`, which tests Lhotse CLI. Ideally, it would...
The docs here mention that TIMIT reports WER, but this dataset typically serves as a benchmark for phone error rate (PER), because it’s one of the few resources that have...
Is sherpa going to have a logo similarly to lhotse, k2, and icefall? Would be nice to visually present it when describing the full ecosystem to others :)
### 🐛 Describe the bug ```python from io import BytesIO import torch import torchaudio torch.manual_seed(0) torchaudio.set_audio_backend("sox_io") sr = 16000 N = sr # in case you can't reproduce, try increasing...
Testing the suggested workaround solution to https://github.com/pytorch/audio/issues/2662
We’re facing some issues with pip and conda installed k2 packages on the CLSP grid since the GitHub actions CI upgraded Ubuntu to 18.04. The issue is that our Debian...
I played around with k2 in a jupyter notebook and found it quite frustrating that every time I perform some incorrect/unexpected operation, it kills the whole Python kernel with a...
I only tested it on Switchboard alone, but ran the data prep for Fisher and I expect it to work OK. We don't have eval2000 data prep yet so it's...
I thought it makes sense to archive this repo in GitHub as it's not being actively developed anymore. It will make it read-only and clearly display it's archived to everybody...