fasttext 0.1.0 → 0.1.1

data/vendor/fastText/crawl/download_crawl.sh

@@ -1,57 +0,0 @@
-#!/bin/usr/env sh
-# Copyright (c) 2018-present, Facebook, Inc.
-# All rights reserved.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-set -e
-
-# Set this variable to the crawl you want to process.
-WET_PATHS_URL="https://commoncrawl.s3.amazonaws.com/crawl-data/CC-MAIN-2018-34/wet.paths.gz"
-
-# Set NUM_LANGID and NUM_DEDUP according to the capacity of your machine.
-# Please note that each dedup process uses 2GB of RAM, while langid is
-# mostly limited by cpu usage.
-NUM_LANGID=12
-NUM_DEDUP=8
-URL="https://commoncrawl.s3.amazonaws.com/"
-
-if [ ! -d fastText ]; then
-    git clone https://github.com/facebookresearch/fastText.git
-fi
-
-if [ ! -f fastText/fasttext ]; then
-    cd fastText
-    make
-    cd ..
-fi
-
-if [ ! -f lid.176.bin ]; then
-    wget https://dl.fbaipublicfiles.com/fasttext/supervised-models/lid.176.bin
-fi
-
-if [ ! -d tmp ]; then
-    mkdir tmp
-fi
-
-if [ ! -d shard ]; then
-    mkdir shard
-fi
-
-if [ ! -f wet.paths ]; then
-    wget "${WET_PATHS_URL}"
-    gunzip wet.paths.gz
-fi
-
-## Language identification
-cat wet.paths | xargs -n 1 -P "${NUM_LANGID}" -I '{}' sh process_wet_file.sh "${URL}{}"
-
-## Deduplication
-g++ -std=c++11 -O3 -o dedup dedup.cc
-g++ -std=c++11 -O3 -o filter_utf8 filter_utf8.cc
-find shard -name '*.txt' | xargs -n 1 -P "${NUM_DEDUP}" -I '{}' sh filter_dedup.sh "{}"
-
-## Example of data filtering + tokenization
-git clone https://github.com/moses-smt/mosesdecoder.git
-perl mosesdecoder/scripts/tokenizer/tokenizer.perl -l es < shard/es.dedup > shard/es.tok

data/vendor/fastText/crawl/filter_dedup.sh

@@ -1,13 +0,0 @@
-#!/bin/usr/env sh
-# Copyright (c) 2018-present, Facebook, Inc.
-# All rights reserved.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-set -e
-
-LG=$(basename --suffix=".txt" "${1}")
-
-./filter_utf8 < "shard/${LG}.txt" \
-    | ./dedup > "shard/${LG}.dedup"

data/vendor/fastText/crawl/filter_utf8.cc

@@ -1,105 +0,0 @@
-// Copyright (c) 2018-present, Facebook, Inc.
-// All rights reserved.
-//
-// This source code is licensed under the MIT license found in the
-// LICENSE file in the root directory of this source tree.
-
-#include <cstdint>
-#include <iostream>
-#include <string>
-
-// Check that the next n bytes are continuation bytes.
-bool continuation(uint8_t* str, int n)
-{
-  for (int i = 0; i < n; i++) {
-    if ((str[i] & 0xc0) != 0x80) return false;
-  }
-  return true;
-}
-
-// Invalid UTF8 correspond to codepoints which are larger than U+10FFFF.
-// This value is encoded in UTF8 as:
-//  * 11110.100 10.001111 10.111111 10.111111
-// We thus check if the first byte is larger than 0xf4, or if it is equal
-// to 0xf4 and the second byte is larger than 0x8f.
-bool invalid(uint8_t* str)
-{
-  return str[0] > 0xf4 || (str[0] == 0xf4 && str[1] > 0x8f);
-}
-
-// Surrogate halves corresponds to the range U+D800 through U+DFFF,
-// which are encoded in UTF8 as:
-//  * 1110.1101 10.100000 10.000000
-//  * 1110.1101 10.111111 10.111111
-// We thus check is the first byte is equal to 0xed and if the
-// sixth bit of the second byte is set.
-bool surrogate(uint8_t* str)
-{
-  return str[0] == 0xed && str[1] & 0x20;
-}
-
-// Sequences of length 2 are overlong if the leading 4 bits (noted as y)
-// are equal to 0: 110.yyyyx 10xxxxxx
-bool overlong_2(uint8_t* str)
-{
-  return (str[0] & 0x1e) == 0;
-}
-
-// Sequences of lenth 3 are overlong if the leading 5 bits (noted as y)
-// are equal to 0: 1110.yyyy 10.yxxxxx 10.xxxxxx
-bool overlong_3(uint8_t* str)
-{
-  return (str[0] & 0x0f) == 0 && (str[1] & 0x20) == 0;
-}
-
-// Sequences of length 4 are overlong if the leading 5 bits (noted as y)
-// are equal to 0: 11110.yyy 10.yyxxxx 10.xxxxxx 10.xxxxxx
-bool overlong_4(uint8_t* str)
-{
-  return (str[0] & 0x07) == 0 && (str[1] & 0x30) == 0;
-}
-
-bool valid_utf8(uint8_t* str, size_t length)
-{
-  uint8_t* end = str + length;
-  while (str < end) {
-    if (str[0] < 0x80) {
-      // 0.xxxxxxx
-      str += 1;
-    } else if ((str[0] & 0xe0) == 0xc0) {
-      // 110.xxxxx 10.xxxxxx
-      if (str + 1 >= end) return false;
-      if (!continuation(str + 1, 1)) return false;
-      if (overlong_2(str)) return false;
-      str += 2;
-    } else if ((str[0] & 0xf0) == 0xe0) {
-      // 1110.xxxx 10.xxxxxx 10.xxxxxx
-      if (str + 2 >= end) return false;
-      if (!continuation(str + 1, 2)) return false;
-      if (overlong_3(str)) return false;
-      if (surrogate(str)) return false;
-      str += 3;
-    } else if ((str[0] & 0xf8) == 0xf0) {
-      // 11110.xxx 10.xxxxxx 10.xxxxxx 10.xxxxxx
-      if (str + 3 >= end) return false;
-      if (!continuation(str + 1, 3)) return false;
-      if (overlong_4(str)) return false;
-      if (invalid(str)) return false;
-      str += 4;
-    } else {
-      return false;
-    }
-  }
-  return true;
-}
-
-int main(int argc, char** argv)
-{
-  std::ios_base::sync_with_stdio(false);
-  for (std::string line; std::getline(std::cin, line);) {
-    if (valid_utf8((uint8_t*) line.data(), line.length())) {
-      std::cout << line << std::endl;
-    }
-  }
-  return 0;
-}

data/vendor/fastText/crawl/process_wet_file.sh

@@ -1,30 +0,0 @@
-#!/bin/usr/env sh
-# Copyright (c) 2018-present, Facebook, Inc.
-# All rights reserved.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-set -e
-
-URL=$1
-
-FILENAME=$(basename --suffix=".warc.wet.gz" "${URL}")
-
-echo "Processing ${FILENAME}."
-
-wget -q -P tmp "${URL}"
-
-#echo "Extracting ${FILENAME}.warc.wet.gz"
-gunzip "tmp/${FILENAME}.warc.wet.gz"
-
-#echo "Language identification for ${FILENAME}.warc.wet"
-fastText/fasttext predict-prob lid.176.bin "tmp/${FILENAME}.warc.wet" > "tmp/${FILENAME}.lid"
-
-#echo "Splitting ${FILENAME}.warc.wet per language"
-paste "tmp/${FILENAME}.lid" "tmp/${FILENAME}.warc.wet" | \
-    awk '($2 > 0.8 || ($1=="__label__hr" && $2 > 0.4)) && length() > 100 {lang = substr($1, 10); $1=""; $2=""; print $0 >> "shard/"lang".txt"}'
-
-#echo "Removing tmp files"
-rm "tmp/${FILENAME}.lid"
-rm "tmp/${FILENAME}.warc.wet"

data/vendor/fastText/docs/aligned-vectors.md

@@ -1,64 +0,0 @@
----
-id: aligned-vectors
-title: Aligned word vectors
----
-
-We are publishing aligned word vectors for 44 languages based on the pre-trained vectors computed on [*Wikipedia*](https://www.wikipedia.org) using fastText.
-The alignments are performed with the RCSLS method described in [*Joulin et al (2018)*](https://arxiv.org/abs/1804.07745).
-
-### Vectors
-
-The aligned vectors can be downloaded from:
-
-|||||
-|-|-|-|-|
-| Afrikaans: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.af.align.vec) | Arabic: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.ar.align.vec) | Bulgarian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.bg.align.vec) | Bengali: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.bn.align.vec) |
-| Bosnian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.bs.align.vec) | Catalan: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.ca.align.vec) | Czech: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.cs.align.vec) | Danish: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.da.align.vec) |
-| German: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.de.align.vec) | Greek: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.el.align.vec) | English: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.en.align.vec) | Spanish: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.es.align.vec) |
-| Estonian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.et.align.vec) | Persian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.fa.align.vec) | Finnish: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.fi.align.vec) | French: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.fr.align.vec) |
-| Hebrew: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.he.align.vec) | Hindi: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.hi.align.vec) | Croatian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.hr.align.vec) | Hungarian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.hu.align.vec) |
-| Indonesian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.id.align.vec) | Italian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.it.align.vec) | Korean: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.ko.align.vec) | Lithuanian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.lt.align.vec) |
-| Latvian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.lv.align.vec) | Macedonian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.mk.align.vec) | Malay: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.ms.align.vec) | Dutch: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.nl.align.vec) |
-| Norwegian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.no.align.vec) | Polish: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.pl.align.vec) | Portuguese: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.pt.align.vec) | Romanian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.ro.align.vec) |
-| Russian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.ru.align.vec) | Slovak: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.sk.align.vec) | Slovenian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.sl.align.vec) | Albanian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.sq.align.vec) |
-| Swedish: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.sv.align.vec) | Tamil: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.ta.align.vec) | Thai: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.th.align.vec) | Tagalog: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.tl.align.vec) |
-| Turkish: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.tr.align.vec) | Ukrainian: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.uk.align.vec) | Vietnamese: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.vi.align.vec) | Chinese: [*text*](https://dl.fbaipublicfiles.com/fasttext/vectors-aligned/wiki.zh.align.vec) |
-
-### Format
-
-The word vectors come in the default text format of fastText.
-The first line gives the number of vectors and their dimension.
-The other lines contain a word followed by its vector. Each value is space separated.
-
-### License
-
-The word vectors are distributed under the [*Creative Commons Attribution-Share-Alike License 3.0*](https://creativecommons.org/licenses/by-sa/3.0/).
-
-### References
-
-If you use these word vectors, please cite the following papers:
-
-[1] A. Joulin, P. Bojanowski, T. Mikolov, H. Jegou, E. Grave, [*Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion*](https://arxiv.org/abs/1804.07745)
-
-```markup
-@InProceedings{joulin2018loss,
-  title={Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion},
-  author={Joulin, Armand and Bojanowski, Piotr and Mikolov, Tomas and J\'egou, Herv\'e and Grave, Edouard},
-  year={2018},
-  booktitle={Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
-}
-```
-
-[2] P. Bojanowski\*, E. Grave\*, A. Joulin, T. Mikolov, [*Enriching Word Vectors with Subword Information*](https://arxiv.org/abs/1607.04606)
-
-```markup
-@article{bojanowski2017enriching,
-  title={Enriching Word Vectors with Subword Information},
-  author={Bojanowski, Piotr and Grave, Edouard and Joulin, Armand and Mikolov, Tomas},
-  journal={Transactions of the Association for Computational Linguistics},
-  volume={5},
-  year={2017},
-  issn={2307-387X},
-  pages={135--146}
-}
-```

data/vendor/fastText/docs/api.md

@@ -1,6 +0,0 @@
----
-id: api
-title:API
----
-
-We automatically generate our [API documentation](/docs/en/html/index.html) with doxygen.

data/vendor/fastText/docs/cheatsheet.md

@@ -1,66 +0,0 @@
----
-id: cheatsheet
-title: Cheatsheet
----
-
-## Word representation learning
-
-In order to learn word vectors do:
-
-```bash
-$ ./fasttext skipgram -input data.txt -output model
-```
-
-## Obtaining word vectors
-
-Print word vectors for a text file `queries.txt` containing words.
-
-```bash
-$ ./fasttext print-word-vectors model.bin < queries.txt
-```
-
-## Text classification
-
-In order to train a text classifier do:
-
-```bash
-$ ./fasttext supervised -input train.txt -output model
-```
-
-Once the model was trained, you can evaluate it by computing the precision and recall at k (P@k and R@k) on a test set using:
-
-```bash
-$ ./fasttext test model.bin test.txt 1
-```
-
-In order to obtain the k most likely labels for a piece of text, use:
-
-```bash
-$ ./fasttext predict model.bin test.txt k
-```
-
-In order to obtain the k most likely labels and their associated probabilities for a piece of text, use:
-
-```bash
-$ ./fasttext predict-prob model.bin test.txt k
-```
-
-If you want to compute vector representations of sentences or paragraphs, please use:
-
-```bash
-$ ./fasttext print-sentence-vectors model.bin < text.txt
-```
-
-## Quantization
-
-In order to create a `.ftz` file with a smaller memory footprint do:
-
-```bash
-$ ./fasttext quantize -output model
-```
-
-All other commands such as test also work with this model
-
-```bash
-$ ./fasttext test model.ftz test.txt
-```

data/vendor/fastText/docs/crawl-vectors.md

@@ -1,125 +0,0 @@
----
-id: crawl-vectors
-title: Word vectors for 157 languages
----
-
-We distribute pre-trained word vectors for 157 languages, trained on [*Common Crawl*](http://commoncrawl.org/) and [*Wikipedia*](https://www.wikipedia.org) using fastText.
-These models were trained using CBOW with position-weights, in dimension 300, with character n-grams of length 5, a window of size 5 and 10 negatives.
-We also distribute three new word analogy datasets, for French, Hindi and Polish.
-
-### Format
-
-The word vectors are available in both binary and text formats.
-
-Using the binary models, vectors for out-of-vocabulary words can be obtained with
-```
-$ ./fasttext print-word-vectors wiki.it.300.bin < oov_words.txt
-```
-where the file oov_words.txt contains out-of-vocabulary words.
-
-In the text format, each line contain a word followed by its vector.
-Each value is space separated, and words are sorted by frequency in descending order.
-These text models can easily be loaded in Python using the following code:
-```python
-import io
-
-def load_vectors(fname):
-    fin = io.open(fname, 'r', encoding='utf-8', newline='\n', errors='ignore')
-    n, d = map(int, fin.readline().split())
-    data = {}
-    for line in fin:
-        tokens = line.rstrip().split(' ')
-        data[tokens[0]] = map(float, tokens[1:])
-    return data
-```
-
-### Tokenization
-
-We used the [*Stanford word segmenter*](https://nlp.stanford.edu/software/segmenter.html) for Chinese, [*Mecab*](http://taku910.github.io/mecab/) for Japanese and [*UETsegmenter*](https://github.com/phongnt570/UETsegmenter) for Vietnamese.
-For languages using the Latin, Cyrillic, Hebrew or Greek scripts, we used the tokenizer from the [*Europarl*](http://www.statmt.org/europarl/) preprocessing tools.
-For the remaining languages, we used the ICU tokenizer.
-
-More information about the training of these models can be found in the article [*Learning Word Vectors for 157 Languages*](https://arxiv.org/abs/1802.06893).
-
-### License
-
-The word vectors are distributed under the [*Creative Commons Attribution-Share-Alike License 3.0*](https://creativecommons.org/licenses/by-sa/3.0/).
-
-### References
-
-If you use these word vectors, please cite the following paper:
-
-E. Grave\*, P. Bojanowski\*, P. Gupta, A. Joulin, T. Mikolov, [*Learning Word Vectors for 157 Languages*](https://arxiv.org/abs/1802.06893)
-
-```markup
-@inproceedings{grave2018learning,
-  title={Learning Word Vectors for 157 Languages},
-  author={Grave, Edouard and Bojanowski, Piotr and Gupta, Prakhar and Joulin, Armand and Mikolov, Tomas},
-  booktitle={Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018)},
-  year={2018}
-}
-```
-
-### Evaluation datasets
-
-The analogy evaluation datasets described in the paper are available here: [French](https://dl.fbaipublicfiles.com/fasttext/word-analogies/questions-words-fr.txt), [Hindi](https://dl.fbaipublicfiles.com/fasttext/word-analogies/questions-words-hi.txt), [Polish](https://dl.fbaipublicfiles.com/fasttext/word-analogies/questions-words-pl.txt).
-
-### Models
-
-The models can be downloaded from:
-
-||||
-|-|-|-|
-|  Afrikaans:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.af.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.af.300.vec.gz) |  Albanian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sq.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sq.300.vec.gz) |  Alemannic:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.als.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.als.300.vec.gz) |
-|  Amharic:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.am.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.am.300.vec.gz) |  Arabic:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ar.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ar.300.vec.gz) |  Aragonese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.an.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.an.300.vec.gz) |
-|  Armenian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hy.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hy.300.vec.gz) |  Assamese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.as.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.as.300.vec.gz) |  Asturian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ast.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ast.300.vec.gz) |
-|  Azerbaijani:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.az.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.az.300.vec.gz) |  Bashkir:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ba.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ba.300.vec.gz) |  Basque:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.eu.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.eu.300.vec.gz) |
-|  Bavarian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bar.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bar.300.vec.gz) |  Belarusian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.be.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.be.300.vec.gz) |  Bengali:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bn.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bn.300.vec.gz) |
-|  Bihari:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bh.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bh.300.vec.gz) |  Bishnupriya Manipuri:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bpy.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bpy.300.vec.gz) |  Bosnian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bs.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bs.300.vec.gz) |
-|  Breton:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.br.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.br.300.vec.gz) |  Bulgarian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bg.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bg.300.vec.gz) |  Burmese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.my.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.my.300.vec.gz) |
-|  Catalan:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ca.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ca.300.vec.gz) |  Cebuano:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ceb.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ceb.300.vec.gz) |  Central Bicolano:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bcl.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bcl.300.vec.gz) |
-|  Chechen:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ce.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ce.300.vec.gz) |  Chinese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.zh.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.zh.300.vec.gz) |  Chuvash:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.cv.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.cv.300.vec.gz) |
-|  Corsican:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.co.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.co.300.vec.gz) |  Croatian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hr.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hr.300.vec.gz) |  Czech:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.cs.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.cs.300.vec.gz) |
-|  Danish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.da.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.da.300.vec.gz) |  Divehi:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.dv.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.dv.300.vec.gz) |  Dutch:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nl.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nl.300.vec.gz) |
-|  Eastern Punjabi:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pa.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pa.300.vec.gz) |  Egyptian Arabic:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.arz.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.arz.300.vec.gz) |  Emilian-Romagnol:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.eml.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.eml.300.vec.gz) |
-|  English: [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.en.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.en.300.vec.gz) |  Erzya:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.myv.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.myv.300.vec.gz) |  Esperanto:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.eo.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.eo.300.vec.gz) |
-|  Estonian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.et.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.et.300.vec.gz) |  Fiji Hindi:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hif.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hif.300.vec.gz) |  Finnish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.fi.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.fi.300.vec.gz) |
-|  French:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.fr.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.fr.300.vec.gz) |  Galician:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.gl.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.gl.300.vec.gz) |  Georgian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ka.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ka.300.vec.gz) |
-|  German:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.de.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.de.300.vec.gz) |  Goan Konkani:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.gom.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.gom.300.vec.gz) |  Greek:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.el.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.el.300.vec.gz) |
-|  Gujarati:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.gu.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.gu.300.vec.gz) |  Haitian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ht.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ht.300.vec.gz) |  Hebrew:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.he.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.he.300.vec.gz) |
-|  Hill Mari:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mrj.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mrj.300.vec.gz) |  Hindi:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hi.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hi.300.vec.gz) |  Hungarian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hu.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hu.300.vec.gz) |
-|  Icelandic:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.is.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.is.300.vec.gz) |  Ido:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.io.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.io.300.vec.gz) |  Ilokano:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ilo.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ilo.300.vec.gz) |
-|  Indonesian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.id.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.id.300.vec.gz) |  Interlingua:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ia.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ia.300.vec.gz) |  Irish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ga.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ga.300.vec.gz) |
-|  Italian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.it.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.it.300.vec.gz) |  Japanese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ja.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ja.300.vec.gz) |  Javanese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.jv.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.jv.300.vec.gz) |
-|  Kannada:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.kn.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.kn.300.vec.gz) |  Kapampangan:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pam.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pam.300.vec.gz) |  Kazakh:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.kk.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.kk.300.vec.gz) |
-|  Khmer:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.km.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.km.300.vec.gz) |  Kirghiz:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ky.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ky.300.vec.gz) |  Korean:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ko.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ko.300.vec.gz) |
-|  Kurdish (Kurmanji):  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ku.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ku.300.vec.gz) |  Kurdish (Sorani):  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ckb.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ckb.300.vec.gz) |  Latin:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.la.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.la.300.vec.gz) |
-|  Latvian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.lv.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.lv.300.vec.gz) |  Limburgish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.li.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.li.300.vec.gz) |  Lithuanian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.lt.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.lt.300.vec.gz) |
-|  Lombard:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.lmo.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.lmo.300.vec.gz) |  Low Saxon:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nds.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nds.300.vec.gz) |  Luxembourgish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.lb.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.lb.300.vec.gz) |
-|  Macedonian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mk.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mk.300.vec.gz) |  Maithili:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mai.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mai.300.vec.gz) |  Malagasy:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mg.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mg.300.vec.gz) |
-|  Malay:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ms.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ms.300.vec.gz) |  Malayalam:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ml.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ml.300.vec.gz) |  Maltese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mt.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mt.300.vec.gz) |
-|  Manx:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.gv.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.gv.300.vec.gz) |  Marathi:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mr.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mr.300.vec.gz) |  Mazandarani:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mzn.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mzn.300.vec.gz) |
-|  Meadow Mari:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mhr.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mhr.300.vec.gz) |  Minangkabau:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.min.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.min.300.vec.gz) |  Mingrelian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.xmf.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.xmf.300.vec.gz) |
-|  Mirandese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mwl.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mwl.300.vec.gz) |  Mongolian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mn.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.mn.300.vec.gz) |  Nahuatl:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nah.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nah.300.vec.gz) |
-|  Neapolitan:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nap.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nap.300.vec.gz) |  Nepali:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ne.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ne.300.vec.gz) |  Newar:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.new.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.new.300.vec.gz) |
-|  North Frisian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.frr.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.frr.300.vec.gz) |  Northern Sotho:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nso.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nso.300.vec.gz) |  Norwegian (Bokmål):  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.no.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.no.300.vec.gz) |
-|  Norwegian (Nynorsk):  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nn.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.nn.300.vec.gz) |  Occitan:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.oc.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.oc.300.vec.gz) |  Oriya:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.or.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.or.300.vec.gz) |
-|  Ossetian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.os.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.os.300.vec.gz) |  Palatinate German:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pfl.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pfl.300.vec.gz) |  Pashto:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ps.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ps.300.vec.gz) |
-|  Persian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.fa.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.fa.300.vec.gz) |  Piedmontese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pms.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pms.300.vec.gz) |  Polish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pl.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pl.300.vec.gz) |
-|  Portuguese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pt.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pt.300.vec.gz) |  Quechua:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.qu.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.qu.300.vec.gz) |  Romanian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ro.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ro.300.vec.gz) |
-|  Romansh:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.rm.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.rm.300.vec.gz) |  Russian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ru.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ru.300.vec.gz) |  Sakha:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sah.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sah.300.vec.gz) |
-|  Sanskrit:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sa.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sa.300.vec.gz) |  Sardinian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sc.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sc.300.vec.gz) |  Scots:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sco.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sco.300.vec.gz) |
-|  Scottish Gaelic:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.gd.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.gd.300.vec.gz) |  Serbian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sr.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sr.300.vec.gz) |  Serbo-Croatian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sh.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sh.300.vec.gz) |
-|  Sicilian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.scn.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.scn.300.vec.gz) |  Sindhi:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sd.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sd.300.vec.gz) |  Sinhalese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.si.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.si.300.vec.gz) |
-|  Slovak:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sk.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sk.300.vec.gz) |  Slovenian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sl.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sl.300.vec.gz) |  Somali:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.so.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.so.300.vec.gz) |
-|  Southern Azerbaijani:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.azb.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.azb.300.vec.gz) |  Spanish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.es.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.es.300.vec.gz) |  Sundanese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.su.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.su.300.vec.gz) |
-|  Swahili:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sw.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sw.300.vec.gz) |  Swedish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sv.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.sv.300.vec.gz) |  Tagalog:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.tl.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.tl.300.vec.gz) |
-|  Tajik:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.tg.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.tg.300.vec.gz) |  Tamil:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ta.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ta.300.vec.gz) |  Tatar:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.tt.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.tt.300.vec.gz) |
-|  Telugu:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.te.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.te.300.vec.gz) |  Thai:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.th.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.th.300.vec.gz) |  Tibetan:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bo.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.bo.300.vec.gz) |
-|  Turkish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.tr.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.tr.300.vec.gz) |  Turkmen:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.tk.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.tk.300.vec.gz) |  Ukrainian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.uk.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.uk.300.vec.gz) |
-|  Upper Sorbian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hsb.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.hsb.300.vec.gz) |  Urdu:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ur.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ur.300.vec.gz) |  Uyghur:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ug.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ug.300.vec.gz) |
-|  Uzbek:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.uz.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.uz.300.vec.gz) |  Venetian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.vec.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.vec.300.vec.gz) |  Vietnamese:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.vi.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.vi.300.vec.gz) |
-|  Volapük:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.vo.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.vo.300.vec.gz) |  Walloon:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.wa.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.wa.300.vec.gz) |  Waray:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.war.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.war.300.vec.gz) |
-|  Welsh:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.cy.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.cy.300.vec.gz) |  West Flemish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.vls.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.vls.300.vec.gz) |  West Frisian:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.fy.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.fy.300.vec.gz) |
-|  Western Punjabi:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pnb.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pnb.300.vec.gz) |  Yiddish:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.yi.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.yi.300.vec.gz) |  Yoruba:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.yo.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.yo.300.vec.gz) |
-|  Zazaki:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.diq.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.diq.300.vec.gz) |  Zeelandic:  [bin](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.zea.300.bin.gz), [text](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.zea.300.vec.gz) |