Problem Tried installing fastText with Python 3.10 and it results in a build failure. Input pip install fasttext Output Defaulting to user installation because normal site-packages is not writeable Collecting fasttext Using cached fasttext-0.9.2.tar.gz (68 kB) Preparing metadata (setup.py) ......

I am member of a research team that is working with Vedic Sanskrit (https://chronbmm.phil.hhu.de/). We wonder whether you would be interested to include a Sanskrit model in the downloadable models on your site? We can provide both the training data as well as the model itself.

Hi team, trying to install fasttext with Python 3.9 results in a failure. Input: pip install fasttext Output: Collecting fasttext Downloading fasttext-0.9.2.tar.gz (68 kB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 68.8/68.8 kB 3.7 MB/s eta 0:00:00 Preparing metadata (setup.py) ... done Colle...

I define a focal loss function which has 3 parts: computeOutput, backprop, and loss. When I train with this new focal loss, it happens loss increase with Progress(should decrease and convergence). Would you pls advise how to modify this focal loss function? In loss.cc, I added focal loss: FocalLoss:...

Source: https://www.kaggle.com/datasets/yekenot/fasttext-crawl-300d-2m

When give make command on the command line, it gives following error: c++ -pthread -std=c++11 -march=native -O3 -funroll-loops -DNDEBUG -c src/args.cc process_begin: CreateProcess(NULL, c++ -pthread -std=c++11 -march=native -O3 -funroll-loops -DNDEBUG -c src/args.cc, ...) failed. make (e=2): The sys...

https://fasttext.cc/docs/en/supervised-tutorial.html#our-first-classifier In the example of how to create first classifier in command line there is mentioned following command: ./fasttext supervised -input cooking.train -output model_cooking The execution leads to following error: terminate called a...

Hi guys, I have been implementing fasttext supervised learning funktion for a multiclass Problem. The results look great, the autotuning of the parameters works great too. It is by far the best perfoming model I have tried on my use case. But I need to Validate the results. Cross Validation would be...

Fails with: [ 13s] c++ -pthread -std=c++11 -O3 -funroll-loops -DNDEBUG -c src/args.cc [ 13s] src/args.cc: In member function 'int64_t fasttext::Args::getAutotuneModelSize() const': [ 13s] src/args.cc:468:3: error: 'uint64_t' was not declared in this scope [ 13s] 468 | uint64_t multiplier...

Hi in the tutorial on the supervised module of fastest in the tutorial we are shown the below results: model = fasttext.train_supervised(input="cooking.train", lr=0.5, epoch=25, wordNgrams=2, bucket=200000, dim=50, loss='ova') model.test("cooking.valid", k=-1) (3000L, 0.702, 0.2) Where the precision...