Duplicate from edugp/kenlm

Co-authored-by: Eduardo Gonzalez Ponferrada <[email protected]>

.gitattributes

@@ -0,0 +1,30 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*sp.model filter=lfs diff=lfs merge=lfs -text
+*sp.vocab filter=lfs diff=lfs merge=lfs -text
+*.arpa filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2021-2022 Eduardo González Ponferrada
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,70 @@
+---
+language:
+- es
+- af
+- ar
+- arz
+- as
+- bn
+- fr
+- sw
+- eu
+- ca
+- zh
+- en
+- hi
+- ur
+- id
+- pt
+- vi
+- gu
+- kn
+- ml
+- mr
+- ta
+- te
+- yo
+tags:
+- kenlm
+- perplexity
+- n-gram
+- kneser-ney
+- bigscience
+license: mit
+datasets:
+- wikipedia
+- oscar
+duplicated_from: edugp/kenlm
+---
+
+# KenLM models
+This repo contains several KenLM models trained on different tokenized datasets and languages.  
+KenLM models are probabilistic n-gram languge models that models. One use case of these models consist on fast perplexity estimation for [filtering or sampling large datasets](https://huggingface.co/bertin-project/bertin-roberta-base-spanish). For example, one could use a KenLM model trained on French Wikipedia to run inference on a large dataset and filter out samples that are very unlike to appear on Wikipedia (high perplexity), or very simple non-informative sentences that could appear repeatedly (low perplexity).
+
+At the root of this repo you will find different directories named after the dataset models were trained on (e.g. `wikipedia`, `oscar`). Within each directory, you will find several models trained on different language subsets of the dataset (e.g. `en (English)`, `es (Spanish)`, `fr (French)`). For each language you will find three different files
+* `{language}.arpa.bin`: The trained KenLM model binary
+* `{language}.sp.model`: The trained SentencePiece model used for tokenization
+* `{language}.sp.vocab`: The vocabulary file for the SentencePiece model
+
+The models have been trained using some of the preprocessing steps from [cc_net](https://github.com/facebookresearch/cc_net), in particular replacing numbers with zeros and normalizing punctuation. So, it is important to keep the default values for the parameters: `lower_case`, `remove_accents`, `normalize_numbers` and `punctuation` when using the pre-trained models in order to replicate the same pre-processing steps at inference time.
+
+# Dependencies
+* KenLM: `pip install https://github.com/kpu/kenlm/archive/master.zip`
+* SentencePiece: `pip install sentencepiece`
+
+# Example:
+```
+from model import KenlmModel
+
+
+# Load model trained on English wikipedia
+model = KenlmModel.from_pretrained("wikipedia", "en")
+
+# Get perplexity
+model.get_perplexity("I am very perplexed")
+# 341.3 (low perplexity, since sentence style is formal and with no grammar mistakes)
+
+model.get_perplexity("im hella trippin")
+# 46793.5 (high perplexity, since the sentence is colloquial and contains grammar mistakes)
+```
+In the example above we see that, since Wikipedia is a collection of encyclopedic articles, a KenLM model trained on it will naturally give lower perplexity scores to sentences with formal language and no grammar mistakes than colloquial sentences with grammar mistakes.

mc4/ig.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7c27f49a2368b603b363f093417352e36a7227cef7a214631050efbd3c04b0
+size 2025000654

mc4/ig.arpa.trie.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557f588644ccca523169495129fa258851a552885ebf400a2a2b9c3d9a26d476
+size 952564451

mc4/ig.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c987d7b1646ba45136dc06d509a1e667a9337f197db54e0472cc09f4ee4f0986
+size 885958

mc4/ig.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca68f0396db1795beac9ca8aa8ed14782fb1cc01c52de7e97b35c5c7b0f0ee91
+size 683760

mc4/ny.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6dbd24886c53dda31f687f0e929473f378d396f97b8cf05bf8e73bdc49e2e2
+size 3556104547

mc4/ny.arpa.trie.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c385e996bd99aacabcc6479616e8ec8c0eac73c8c1064e68649bc0fc283741cb
+size 1694641098

mc4/ny.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d45d61f40c2df9f20a85749f43724ad2f475b6ba2fb09d86db2983719cfc2b25
+size 902895

mc4/ny.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4367a6be4ca21743c2c465c731d0b3f8c6bfe4bbd2355f79ff1ea64ed5515988
+size 700958

mc4/sn.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:039060e9ac7db9039c1141c6ba231b4e1cf97a5aee63aeb1f4641042fc08bd4c
+size 4802972178

mc4/sn.arpa.trie.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bc0994e6cd2783dda3a23e257727aa28e833f72cdc95be2406b102a2edea25
+size 2331081939

mc4/sn.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d52abd2c26da133b6901ef3bfda12d032e7c7e90b668c6c41ab2a179dc66aa
+size 900223

mc4/sn.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ee54644a596b0d5f476eaf68726ee442834d9bdcef97716bb7aeb8d758130e
+size 698093

mc4/st.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1aa917b1f02c4fb2b6927ce2dc46e50d5f8171dc375d333207ddb06c0dbd6d6
+size 2103573048

mc4/st.arpa.trie.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611c4bc26db22fbf4abdc396dd25f9138da577c6ace9997e12a172387d58270f
+size 984849770

mc4/st.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a8e2d5442162fa975ef8bfbdbd2201eaf98bec71ab614bd74036a287974b538
+size 922202

mc4/st.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987599705afc4ad40b02282871783a40464991c9d2cabd529217b049d6371446
+size 720086

mc4/xh.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c5cb3fee548ce0629849d47747d141efff1b2de7c9dc5e2be166f946b072b8
+size 1917154691

mc4/xh.arpa.trie.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013bbccd45e9c775e511870e163b7e03a18bd1e2092c9e283b817b5b47149ba9
+size 928523775

mc4/xh.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4278c5447178104c6b689b6e7d85b59cbfe8a9e9054eb5ee47267f9ca86b91
+size 899309

mc4/xh.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1ef95b95c11a58262d7975acaa3bfc8aaaa23baf731b7c535ec4fa97b35c79
+size 697154

mc4/zu.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1393f05347e426060fa98d5b8a763834b35b513579d32ff9937446855283bf
+size 6377741974

mc4/zu.arpa.trie.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d9ec365a667f6061a96f8592cacde990d8dda18783b847dfb4ad7b650de21c
+size 3105856237

mc4/zu.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8242c97953d7f31ad00a36fd4b3ea347eb056a5c2a97ceeae983273a8430adb
+size 868576

mc4/zu.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0230bbd8d49a103701575ee218420589ee52a644c172084017522fc0733a74f6
+size 666409

model.py

@@ -0,0 +1,163 @@
+import os
+import re
+import unicodedata
+from typing import Dict
+
+import kenlm
+import sentencepiece
+from huggingface_hub import cached_download, hf_hub_url
+
+
+class SentencePiece:
+    def __init__(
+        self,
+        model: str,
+    ):
+        super().__init__()
+        self.sp = sentencepiece.SentencePieceProcessor()
+        self.sp.load(str(model))
+
+    def do(self, text: dict) -> dict:
+        tokenized = self.sp.encode_as_pieces(text)
+        return " ".join(tokenized)
+
+
+class KenlmModel:
+    digit_re: re.Pattern = re.compile(r"\d")
+    unicode_punct: Dict[str, str] = {
+        "，": ",",
+        "。": ".",
+        "、": ",",
+        "„": '"',
+        "”": '"',
+        "“": '"',
+        "«": '"',
+        "»": '"',
+        "１": '"',
+        "」": '"',
+        "「": '"',
+        "《": '"',
+        "》": '"',
+        "´": "'",
+        "∶": ":",
+        "：": ":",
+        "？": "?",
+        "！": "!",
+        "（": "(",
+        "）": ")",
+        "；": ";",
+        "–": "-",
+        "—": " - ",
+        "．": ". ",
+        "～": "~",
+        "’": "'",
+        "…": "...",
+        "━": "-",
+        "〈": "<",
+        "〉": ">",
+        "【": "[",
+        "】": "]",
+        "％": "%",
+        "►": "-",
+    }
+    unicode_punct_re = re.compile(f"[{''.join(unicode_punct.keys())}]")
+    non_printing_chars_re = re.compile(
+        f"[{''.join(map(chr, list(range(0,32)) + list(range(127,160))))}]"
+    )
+    kenlm_model_dir = None
+    sentence_piece_model_dir = None
+
+    def __init__(
+        self,
+        model_dataset: str,
+        language: str,
+        lower_case: bool = False,
+        remove_accents: bool = False,
+        normalize_numbers: bool = True,
+        punctuation: int = 1,
+    ):
+        self.model = kenlm.Model(os.path.join(model_dataset, f"{language}.arpa.bin"))
+        self.tokenizer = SentencePiece(os.path.join(model_dataset, f"{language}.sp.model"))
+        self.accent = remove_accents
+        self.case = lower_case
+        self.numbers = normalize_numbers
+        self.punct = punctuation
+
+    @classmethod
+    def from_pretrained(
+        cls,
+        model_dataset: str,
+        language: str,
+    ):
+        return cls(
+            model_dataset,
+            language,
+            False,
+            False,
+            True,
+            1,
+        )
+
+    def pp(self, log_score, length):
+        return 10.0 ** (-log_score / length)
+
+    def get_perplexity(self, doc: str, normalize_cc_net: bool = True):
+        if normalize_cc_net:
+            doc = self.normalize(
+                doc,
+                accent=self.accent,
+                case=self.case,
+                numbers=self.numbers,
+                punct=self.punct,
+            )
+        # Tokenize (after normalizing): See https://github.com/facebookresearch/cc_net/blob/bda555bd1cf1ee2e0b925363e62a61cd46c8b60d/cc_net/mine.py#L352 for full pipeline
+        doc = self.tokenizer.do(doc)
+        doc_log_score, doc_length = 0, 0
+        for line in doc.split("\n"):
+            log_score = self.model.score(line)
+            length = len(line.split()) + 1
+            doc_log_score += log_score
+            doc_length += length
+        return round(self.pp(doc_log_score, doc_length), 1)
+
+    def normalize(
+        self,
+        line: str,
+        accent: bool = True,
+        case: bool = True,
+        numbers: bool = True,
+        punct: int = 1,
+    ) -> str:
+        line = line.strip()
+        if not line:
+            return line
+        if case:
+            line = line.lower()
+        if accent:
+            line = self.strip_accents(line)
+        if numbers:
+            line = self.digit_re.sub("0", line)
+        if punct == 1:
+            line = self.replace_unicode_punct(line)
+        elif punct == 2:
+            line = self.remove_unicode_punct(line)
+        line = self.remove_non_printing_char(line)
+        return line
+
+    def strip_accents(self, line: str) -> str:
+        """Strips accents from a piece of text."""
+        nfd = unicodedata.normalize("NFD", line)
+        output = [c for c in nfd if unicodedata.category(c) != "Mn"]
+        if len(output) == line:
+            return line
+        return "".join(output)
+
+    def replace_unicode_punct(self, text: str) -> str:
+        return "".join(self.unicode_punct.get(c, c) for c in text)
+
+    def remove_unicode_punct(self, text: str) -> str:
+        """More aggressive version of replace_unicode_punct but also faster."""
+        return self.unicode_punct_re.sub("", text)
+
+    def remove_non_printing_char(self, text: str) -> str:
+        return self.non_printing_chars_re.sub("", text)

oscar/af.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1c7a15e7dc4552fbe331387cf1d2aa9b2995354ff58743969d943e4fbc9a2b
+size 1699310488

oscar/af.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3249527d2b6fff0db32f3feeadf4acc806034c58aa2877b7804c1dbd079faf0
+size 965654

oscar/af.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141388a76a9e49b671152fe2962f8114e2aab1fef540751f385a10e6dd0fe3a6
+size 763598

oscar/ar.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e845ca65266408136026abc25279a7e9df45d6d4c48a16f15fcbcacb48ffd43
+size 22880497746

oscar/ar.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b367b53707607953aeb7ca5e28d6904aedae50278cdd799fd15e5d5088bd4b
+size 1073054

oscar/ar.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd019d3c9e386bdbaeb1e37a6faeb2457b761142a852f2a9e97ef79dffbb6254
+size 870884

oscar/arz.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d84ceb2b604df092a6862acc780f13d294ffcee482a6fdda418e0f2b0c83b87
+size 288231441

oscar/arz.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98bc5055ff7f03c83c37da78933399ab5d13e26fa9ae634d95a8a4c1360e895
+size 1063144

oscar/arz.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e05eb13200da58a46dc4feec9d2daac5c167f11caf5aed860aca503c4122e77
+size 861047

oscar/as.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f0bef94b578617b8bd942b108938496a1c21e9be8b645db256bc3e54fedb54
+size 410830531

oscar/as.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e5d588d095646ba80f0cfd15e83d418852fde6d97861bc6c4ba655f4b06d476
+size 1274635

oscar/as.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3e4bc59c25b48174798a378e433b2d966fdfc3ac84ded0519348d953bc4ece
+size 1072886

oscar/bn.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50fe651938e0286e9b0be63d212658573dd5ed3f1e6061d09f006bc5393a114a
+size 16813119142

oscar/bn.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd007f17eb669e546d0564896b514a8816cf1805b7ef1ab53879fcf467f49410
+size 1367929

oscar/bn.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c51b211e9e184239c53e9bca1b44e56e728c55802adc6854d8ef9c9ba0a74c9
+size 1165756

oscar/ca.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1f9b6be02b3df19df0ba55ff697607ef7b4ca3a5045a4211f2c4f6ca9ee788
+size 12565197725

oscar/ca.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8ac5a125f25995996995f4ac14acfcfdf8125657e22ab0b6897b39044d22b9
+size 960913

oscar/ca.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e30e0486b473439e2c96eae51689b220529e40de7e6eee8f586ffc09afb89d3b
+size 758607

oscar/en.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c85daa6f6a85d4e4ec14b1695d82bdc47ca6fd8f8034ecc4947e383aadf0d6f8
+size 34132973800

oscar/en.sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d81c313df13d5194f65a7ef37d583934f4c151091c68c70a72625f98232c7223
+size 936812

oscar/en.sp.vocab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a08d8e45267868c780d86c7ae2829bd00dec3621bf991bb99ed4deafb36c88d
+size 734613

oscar/es.arpa.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7665a9e1a610104827a3c4e6c4b86a3a6c4a9507f7fd74a2e06673134d39bf62
+size 21752241307