LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence
☆61Feb 21, 2022Updated 4 years ago
Alternatives and similar repositories for SmallInitEmb
Users that are interested in SmallInitEmb are comparing it to the libraries listed below
Sorting:
- High-performance tokenized language data-loader for Python C++ extension☆14Jul 22, 2024Updated last year
- Efficient optimizers☆294Updated this week
- ☆22Jul 30, 2025Updated 7 months ago
- ☆22Nov 9, 2024Updated last year
- Code for the paper: How Much Context Does My Attention-Based ASR System Need?☆10Mar 8, 2026Updated last week
- High-performance, semantic turn detection for conversational AI☆35Oct 1, 2025Updated 5 months ago
- RWKV, in easy to read code☆73Mar 25, 2025Updated 11 months ago
- recipe for training fully-featured self supervised image jepa models☆12Jun 4, 2025Updated 9 months ago
- gzip Predicts Data-dependent Scaling Laws☆34May 28, 2024Updated last year
- ☆23Aug 26, 2023Updated 2 years ago
- Glow-TTS with Stochastic Duration Predictor and Stochastic Pitch Predictor☆18Jun 5, 2023Updated 2 years ago
- AI model for making mazes that extends OpenAIs GPT2 model☆15Dec 21, 2023Updated 2 years ago
- Text-To-Speech for NotebookLM☆39Jul 20, 2025Updated 8 months ago
- Code for Zero-Shot Tokenizer Transfer☆143Jan 14, 2025Updated last year
- ☆16Jun 13, 2022Updated 3 years ago
- Implementation of Hyena Hierarchy in JAX☆10Apr 30, 2023Updated 2 years ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆119Sep 22, 2024Updated last year
- [ICASSP'26] Real-time streaming voice anonymization & voice conversion☆60Updated this week
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆71Sep 25, 2024Updated last year
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Apr 22, 2025Updated 10 months ago
- Audio-JEPA is an adaptation of the Joint-Embedding Predictive Architecture (JEPA) for self-supervised audio representation learning. Buil…☆42Updated this week
- H-Net Dynamic Hierarchical Architecture☆81Sep 11, 2025Updated 6 months ago
- More than Just Words: Modeling Non-textual Characteristics of Podcasts☆26Nov 6, 2019Updated 6 years ago
- utilities for loading and running text embeddings with onnx☆45Aug 16, 2025Updated 7 months ago
- ESLTTS dataset☆16Feb 6, 2025Updated last year
- Interface Design for Self-Supervised Speech Models, Accepted to Interspeech2024☆16Nov 19, 2024Updated last year
- A minimal Pytorch Implementation of Stochastically Quantized Variational AutoEncoder (SQ-VAE) by Sony☆34Oct 16, 2023Updated 2 years ago
- ☆92Jul 5, 2024Updated last year
- ☆44Sep 19, 2024Updated last year
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28May 4, 2025Updated 10 months ago
- Computing calibrated prediction intervals for neural network regressors☆10May 28, 2019Updated 6 years ago
- Memory-efficient transformer. Work in progress.☆19Sep 17, 2022Updated 3 years ago
- ☆15Mar 15, 2022Updated 4 years ago
- This repository implement a novel zero-shot TTS framework, named Flamed-TTS, focusing on the efficient generation and dynamic pacing in …☆57Aug 9, 2025Updated 7 months ago
- AI eXplainable Inference & Search. Open Sourcing on-premise, ultra-fast latency intelligence to all.☆37Feb 28, 2025Updated last year
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆138Apr 30, 2024Updated last year
- ☆11Jun 5, 2024Updated last year
- ☆36Sep 6, 2025Updated 6 months ago
- ☆16Dec 29, 2024Updated last year