Efficient NLP

@UCVm5B8leEcAeeUmd8P2AliQ - 18.7K subscribers

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: www.linkedin.com/in/libai/

Home Videos Live Playlists

What NoGIL Python means for machine learning

What NoGIL Python means for machine learning Efficient NLP

13.7K views - 2 months ago

Inference Characteristics of Streaming Speech Recognition

Inference Characteristics of Streaming Speech Recognition Efficient NLP

2.6K views - 6 months ago

How to measure LLM writing quality when there is no right answer?

How to measure LLM writing quality when there is no right answer? Efficient NLP

2.1K views - 9 months ago

Train your own writing style with Voice Writer

Train your own writing style with Voice Writer Efficient NLP

470 views - 10 months ago

Training LLM to play chess using Deepseek GRPO reinforcement learning

Training LLM to play chess using Deepseek GRPO reinforcement learning Efficient NLP

18.5K views - 11 months ago

The Most Accurate Speech-to-text APIs in 2025

The Most Accurate Speech-to-text APIs in 2025 Efficient NLP

17.5K views - 1 year ago

Structured Output from LLMs: Grammars, Regex, and State Machines

Structured Output from LLMs: Grammars, Regex, and State Machines Efficient NLP

7.9K views - 1 year ago

Speech LLMs: Models that listen and talk back

Speech LLMs: Models that listen and talk back Efficient NLP

17.6K views - 1 year ago

The Architecture of Chrome Extension Permissions

The Architecture of Chrome Extension Permissions Efficient NLP

2.9K views - 1 year ago

Voice Writer for Chrome

Voice Writer for Chrome Efficient NLP

726 views - 1 year ago

When is a Biased Estimator Better? A Look at Ratio Estimators

When is a Biased Estimator Better? A Look at Ratio Estimators Efficient NLP

1.3K views - 1 year ago

AI-generated text: Detection methods and countermeasures

AI-generated text: Detection methods and countermeasures Efficient NLP

2.3K views - 1 year ago

Residual Vector Quantization for Audio and Speech Embeddings

Residual Vector Quantization for Audio and Speech Embeddings Efficient NLP

10.4K views - 1 year ago

Introducing Voice Writer

Introducing Voice Writer Efficient NLP

3.4K views - 1 year ago

Can Whisper be used for real-time streaming ASR?

Can Whisper be used for real-time streaming ASR? Efficient NLP

38K views - 1 year ago

Top 10 most cited and influential papers in the history of NLP

Top 10 most cited and influential papers in the history of NLP Efficient NLP

2.1K views - 1 year ago

Fine-tuning Whisper to learn my Chinese dialect (Teochew)

Fine-tuning Whisper to learn my Chinese dialect (Teochew) Efficient NLP

17.3K views - 2 years ago

A better Hugging Face model search with OpenAI, RAG, pgvector

A better Hugging Face model search with OpenAI, RAG, pgvector Efficient NLP

2K views - 2 years ago

Speculative Decoding: When Two LLMs are Faster than One

Speculative Decoding: When Two LLMs are Faster than One Efficient NLP

31K views - 2 years ago

Exploring the 24 Areas of Natural Language Processing Research

Exploring the 24 Areas of Natural Language Processing Research Efficient NLP

3.5K views - 2 years ago

Rotary Positional Embeddings: Combining Absolute and Relative

Rotary Positional Embeddings: Combining Absolute and Relative Efficient NLP

71.5K views - 2 years ago

The KV Cache: Memory Usage in Transformers

The KV Cache: Memory Usage in Transformers Efficient NLP

99.4K views - 2 years ago

Quantization vs Pruning vs Distillation: Optimizing NNs for Inference

Quantization vs Pruning vs Distillation: Optimizing NNs for Inference Efficient NLP

60K views - 2 years ago

How is Beam Search Really Implemented?

How is Beam Search Really Implemented? Efficient NLP

25.8K views - 2 years ago

Non-Autoregressive and Shallow Decoding: Speeding up Translation

Non-Autoregressive and Shallow Decoding: Speeding up Translation Efficient NLP

1.9K views - 2 years ago

Which transformer architecture is best? Encoder-only vs Encoder-decoder vs Decoder-only models

Which transformer architecture is best? Encoder-only vs Encoder-decoder vs Decoder-only models Efficient NLP

47.2K views - 2 years ago