VarunGumma / fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
☆18Updated last week
Related projects: ⓘ
- Library for pruning experts per language pair in NLLB-200☆26Updated last year
- Repository containing the open source code of works published at the FBK MT unit.☆41Updated 2 months ago
- Bicleaner fork that uses neural networks☆37Updated last month
- This tool helps automatic generation of grammatically valid synthetic Code-mixed data by utilizing linguistic theories such as Equivalenc…☆52Updated last month
- Implementation of "SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages" paper, accepted to E…☆18Updated last year
- OpusCleaner is a web interface that helps you select, clean and schedule your data for training machine translation models.☆45Updated last week
- Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.☆73Updated last week
- Universal Romanizer that can convert any unicode script to roman (latin) script☆145Updated last month
- A survey of corpora for Germanic low-resource languages and dialects☆24Updated last month
- Official code for Wav2Seq☆95Updated 2 years ago
- NTREX -- News Test References for MT Evaluation☆73Updated 3 months ago
- A toolkit for Spoken Language Understanding Evaluation (SLUE) benchmark. Refer paper https://arxiv.org/abs/2111.10367 for more details. O…☆60Updated 6 months ago
- Tool to fix bitexts and tag near-duplicates for removal☆29Updated last month
- Reduce the size of pretrained Hugging Face models via vocabulary trimming.☆39Updated last year
- Curriculum training☆15Updated this week
- A library for minimum Bayes risk (MBR) decoding☆26Updated 3 weeks ago
- Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages -- ACL 2023☆96Updated 5 months ago
- BLOOM+1: Adapting BLOOM model to support a new unseen language☆69Updated 6 months ago
- SHAS: Approaching optimal Segmentation for End-to-End Speech Translation☆37Updated last year
- SiLLM is a Simultaneous Machine Translation (SiMT) Framework. It utilizes a Large Language model as the translation model and employs a t…☆14Updated 6 months ago
- MAMMOTH: MAssively Multilingual Modular Open Translation @ Helsinki☆21Updated this week
- A guide to building language technology in new languages.☆57Updated 2 years ago
- A tiny BERT for low-resource monolingual models☆28Updated 4 months ago
- ☆38Updated last year
- Morfessor EM+Prune☆10Updated 4 years ago
- Repository accompanying "An Open Dataset and Model for Language Identification" (Burchell et al., 2023)☆65Updated 4 months ago
- This repository implements SummaryMixing, a simpler, faster and much cheaper replacement to self-attention for automatic speech recogniti…☆102Updated this week
- Finite-state script normalization and processing utilities☆36Updated this week
- ☆32Updated 3 years ago
- A repository containing the code for speech translation papers.☆21Updated 2 years ago