M. Yusuf Sarıgöz
M. Yusuf Sarıgöz
[awesome-metric-learning](https://github.com/qdrant/awesome-metric-learning) is a curated list of awesome practical metric learning resources and its applications.
This is still WIP, so consider it as a draft for now. Closes #163. I'm adding commits after small refactoring and polishing comments. Will request a review afterwards.
- Paper: https://arxiv.org/pdf/1912.06798.pdf - Reference for implementation: https://github.com/msight-tech/research-xbm/ ## How it works - XBM relies on the observation that the drift of embeddings is slow during training, i.e., embeddings for...
Don't merge this PR --only for experimentation.
Needs attension and discussion. It's particularly important when users work in places such as Colab.
Based on the discussion in #38 - `quaterion new project-name` to create a basic template with cookie-cutter. - This template may include the basic proper structure, e.g., files such as...
`TensorFlowASR` makes it quite easy to train and deploy almost SOTA ASR models, but it provides a pretrained model only in English. On the other hand, FAIR has recently published...
Hi, Self-supervised pretraining for speech representation is a promising technique for developing ASR in resource-constraint languages with little transcribed data, and SimCLR is applied with success for this purpose in...
Hi, The readme file links to the APK of an Android sample, but I couldn't find the source code. Has it been published somewhere already?
`SequenceGenerator` ported from Fairseq to the `add-transformers` branch work well with the tiny variant, but its performance degrades considerably for larger models. I tried [newly added Colab notebook](https://colab.research.google.com/drive/1Ho81RBV8jysZ7e0FhsSCk_v938QeDuy3?usp=sharing) with other...