VarunGumma / fairseqLinks
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
☆25Updated last month
Alternatives and similar repositories for fairseq
Users that are interested in fairseq are comparing it to the libraries listed below
Sorting:
- Library for pruning experts per language pair in NLLB-200☆34Updated 2 years ago
- NTREX -- News Test References for MT Evaluation☆86Updated last year
- Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages -- ACL 2023☆106Updated last year
- Repository containing the open source code of works published at the FBK MT unit.☆54Updated 3 months ago
- A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB te…☆283Updated last week
- OpusCleaner is a web interface that helps you select, clean and schedule your data for training machine translation models.☆52Updated 2 weeks ago
- BLOOM+1: Adapting BLOOM model to support a new unseen language☆74Updated last year
- Repository accompanying "An Open Dataset and Model for Language Identification" (Burchell et al., 2023)☆74Updated 6 months ago
- A library for minimum Bayes risk (MBR) decoding☆49Updated last week
- Universal Romanizer that can convert any unicode script to roman (latin) script☆226Updated last year
- Bicleaner fork that uses neural networks☆39Updated 4 months ago
- Implementation of "SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages" paper, accepted to E…☆25Updated 2 years ago
- A guide to building language technology in new languages.☆59Updated 3 years ago
- An official implementation of "BPE-Dropout: Simple and Effective Subword Regularization" algorithm.☆52Updated 4 years ago
- Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.☆84Updated last year
- The FLORES+ Machine Translation Benchmark☆108Updated 11 months ago
- This repo contains a set of neural transducer, e.g. sequence-to-sequence model, focusing on character-level tasks.☆76Updated 2 years ago
- ☆31Updated last year
- Reduce the size of pretrained Hugging Face models via vocabulary trimming.☆47Updated 2 years ago
- Curriculum training☆18Updated 3 months ago
- This tool helps automatic generation of grammatically valid synthetic Code-mixed data by utilizing linguistic theories such as Equivalenc…☆56Updated last year
- Official implementation of "GPT or BERT: why not both?"☆61Updated 2 months ago
- SIGMORPHON 2022 Shared Task on Morpheme Segmentation☆28Updated 2 years ago
- Code and data for the paper "Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?"☆25Updated 4 months ago
- Suite for phonetic word embeddings, especially their evaluation and baseline models.☆34Updated 7 months ago
- Vocabulary Trimming (VT) is a model compression technique, which reduces a multilingual LM vocabulary to a target language by deleting ir…☆56Updated 11 months ago
- A tool that locates, downloads, and extracts machine translation corpora☆158Updated last month
- [EMNLP'23] Official Code for "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models"☆34Updated 4 months ago
- MorphyNet: a Large Multilingual Database of Derivational and Inflectional Morphology (+morpheme segmentation)☆51Updated 2 years ago
- Scripts to create speech corpora from open.bible☆13Updated 3 years ago