Efficient NLP
Efficient NLP
My name is Bai Li, I'm a machine learning engineer and PhD in natural language processing. Reach me at:
Email: [email protected]
LinkedIn: https://www.linkedin.com/in/libai/
Inference Characteristics of Streaming Speech Recognition
How to measure LLM writing quality when there is no right answer?
Train your own writing style with Voice Writer
Training LLM to play chess using Deepseek GRPO reinforcement learning
The Most Accurate Speech-to-text APIs in 2025
Structured Output from LLMs: Grammars, Regex, and State Machines
Магистратура по речевым технологиям: модели, которые слушают и отвечают
The Architecture of Chrome Extension Permissions
When is a Biased Estimator Better? A Look at Ratio Estimators
AI-generated text: Detection methods and countermeasures
Residual Vector Quantization for Audio and Speech Embeddings
Можно ли использовать Whisper для потоковой передачи ASR в реальном времени?
Top 10 most cited and influential papers in the history of NLP
Fine-tuning Whisper to learn my Chinese dialect (Teochew)
A better Hugging Face model search with OpenAI, RAG, pgvector
Speculative Decoding: When Two LLMs are Faster than One
Exploring the 24 Areas of Natural Language Processing Research
Поворотные позиционные вложения: сочетание абсолютного и относительного
The KV Cache: Memory Usage in Transformers
Квантование против обрезки против дистилляции: оптимизация нейронных сетей для вывода
Как на самом деле реализован Beam Search?
Non-Autoregressive and Shallow Decoding: Speeding up Translation
Какая архитектура трансформатора лучше? Модели только с энкодером, энкодером и декодером, модели ...