Gowtham.R
Hello, I tried running _tensorboard --logdir graphs/style_stranfer_ after running the style_transfer_sol.py. I couldn't visualize the graph and am getting _No dashboards are active for the current data set_ . I...
The mask function defined in the modules.py expects key_masks to be a 2d-tensor of shape (N, T_k), but the comments describe it as a 3d tensor. (N, 1, T_k).
This [paper](https://arxiv.org/pdf/2103.00854.pdf) introduces the Vyakarana benchmark and they have some syntactic and some sentence-level tasks: - PoS Tagging - Syntax Tree-depth Prediction - Grammatical Case Marking - Subject-Verb Agreement Dataset:...
Seems to have lots of raw audio for low-resource languages.
Dataset link: https://github.com/cardiffnlp/xlm-t/tree/main/data/sentiment/hindi ^ it is in Latin script and contains a mix of English and Hindi Twitter tweets.
Hello, I took a look at [benchmarks page](https://github.com/VKCOM/YouTokenToMe/blob/master/benchmark.md) I wanted to know how YouTokenToMe's speed compares to [subword-nmt](https://github.com/rsennrich/subword-nmt) and is there a reason why it was left out of the...
Hello, I preprocessed some Dicom files and dumped it in blosc format. I did see that dumping as DICOM was not implemented. Is there a way to convert blosc to...
Hey, Thanks for this amazing repository. I was trying to visualize the CAM maps in solution.ipynb but run into an error when I try to run `overlay = img.array_to_img(valid_cam[0]).resize((800,600), Image.BILINEAR).convert('RGB')`....
Hello, Thanks for open sourcing the data-acquisition pipeline. I was looking at [youtube-pipeline-config](https://github.com/Open-Speech-EkStep/data-acquisition-pipeline/blob/f94eec921c53b0cb84e06745dccad0128b525595/data_acquisition_framework/configs/youtube_pipeline_config.py) and the list of channels seems to Kannda specific. Do you have similar lists for other Indian...