-
**Post test results + useful remarks here, ideally of both:**
- the new model (20240117), and
- the base model (kaldi_model_daanzu_20211030-mediumlm)
, using the same test data, and using the d…
-
There are XR use cases (e.g., "audio AR") that could build on poses and other capabilities exposed by core WebXR (and future extensions). The current spec language, though, appears to require visual d…
-
Pose a question about one of the following articles:
[“Machine Learning as a Tool for Hypothesis Generation”](https://doi.org/10.1093/qje/qjad055), Jens Ludwig, Sendhil Mullainathan. The Quarterly…
-
Pose a question about one of the following articles:
“[Online images amplify gender bias](https://www.nature.com/articles/s41586-024-07068-x),” 2024. Guilbeault, Douglas, Solène Delecourt, Tasker …
-
-
Hello,
I was trying to load a finetuned model for the VSR task. I followed the indications on the repository and the jupyter notebook (below you can see that I tried to import modules from the avhu…
-
Vocaluxe doesn't support Rap Notes at all, which USDX does since it's last release in 2017. Even worse, if a song contains a rap note, Vocaluxe ignores the whole song.
From my understanding, rap note…
-
There appears to be a memory leak introduced in v1.65.x with C++ and using Google Speech To Text v1p1beta1 and v2 StreamingRecognize. The same code does not leak with v1.64.1 and v1.64.3 (and none not…
-
### News
- 정부부처/지자체 모두 ChatGPT & 초거대AI 열공 모드: 앞으로 더많이 할 듯..
- [교육부](https://n.news.naver.com/mnews/article/079/0003736942?sid=102), [과기정통부](https://n.news.naver.com/mnews/article/421/0006645964?si…
-
Some ideas floated in our meeting today:
- Reading on speech models
- Reading on hip-hop, lyrics, and language
- Reading on attention mechanisms in deep learning
- Workshopping figures or code i…