Natural language processing

This issue is about the working group specially created for this task. If you are interested in helping out, take a look at this organization, or add me on Discord: ChainYo#3610

We are looking for contributing to HuggingFace's ONNX implementation for all available models on the HF's hub. There is already a lot of architectures implemented for converting PyTorch m

In gensim/models/fasttext.py:

    model = FastText(
        vector_size=m.dim,
        vector_size=m.dim,
        window=m.ws,
        window=m.ws,
        epochs=m.epoch,
        epochs=m.epoch,
        negative=m.neg,
        negative=m.neg,
        # FIXME: these next 2 lines read in unsupported FB FT modes (loss=3 softmax or loss=4 onevsall,
        # or model=3 supervi

Describe the bug

Streaming Datasets can't be pickled, so any interaction between them and multiprocessing results in a crash.

Steps to reproduce the bug

import transformers
from transformers import Trainer, AutoModelForCausalLM, TrainingArguments
import datasets

ds = datasets.load_dataset('oscar', "unshuffled_deduplicated_en", split='train', streaming=True).with_format("

Is your feature request related to a problem? Please describe.
I typically used compressed datasets (e.g. gzipped) to save disk space. This works fine with AllenNLP during training because I can write my dataset reader to load the compressed data. However, the predict command opens the file and reads lines for the Predictor. This fails when it tries to load data from my compressed files.

Rather than simply caching nltk_data until the cache expires and it's forced to re-download the entire nltk_data, we should perform a check on the index.xml which refreshes the cache if it differs from some previous cache.

I would advise doing this in the same way that it's done for requirements.txt:
https://github.com/nltk/nltk/blob/59aa3fb88c04d6151f2409b31dcfe0f332b0c9ca/.github/wor