facebookresearch / fairseq2
FAIR Sequence Modeling Toolkit 2
☆891Updated this week
Alternatives and similar repositories for fairseq2:
Users that are interested in fairseq2 are comparing it to the libraries listed below
- SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.☆736Updated 3 weeks ago
- A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB te…☆272Updated 3 months ago
- NeMo text processing for ASR and TTS☆324Updated this week
- Code for the ALiBi method for transformer language models (ICLR 2022)☆524Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,242Updated last month
- SimulEval: A General Evaluation Toolkit for Simultaneous Translation☆112Updated 7 months ago
- Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate☆560Updated 5 months ago
- Helpful tools and examples for working with flex-attention☆726Updated 2 weeks ago
- A pytorch quantization backend for optimum☆922Updated last week
- Large Context Attention☆704Updated 3 months ago
- This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples a…☆550Updated 10 months ago
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆549Updated 3 months ago
- Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch☆649Updated 6 months ago
- Library for Textless Spoken Language Processing☆540Updated last year
- Minimalistic large language model 3D-parallelism training☆1,808Updated this week
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆511Updated 6 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,512Updated 10 months ago
- Code for BLT research paper☆1,513Updated last week
- CoVoST: A Large-Scale Multilingual Speech-To-Text Translation Corpus (CC0 Licensed)☆376Updated 3 years ago
- Language Modeling with the H3 State Space Model☆520Updated last year
- Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".☆429Updated last year
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,542Updated 5 months ago
- AcademiCodec: An Open Source Audio Codec Model for Academic Research☆610Updated last year
- dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.☆494Updated last year
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆692Updated last year
- SALMONN: Speech Audio Language Music Open Neural Network☆1,211Updated last month
- PyTorch extensions for high performance and large scale training.☆3,306Updated 2 weeks ago
- Cramming the training of a (BERT-type) language model into limited compute.☆1,331Updated 10 months ago
- Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis☆918Updated 8 months ago
- Thunder gives you PyTorch models superpowers for training and inference. Unlock out-of-the-box optimizations for performance, memory and …☆1,328Updated this week