What NoGIL Python means for machine learning
Efficient NLP
What NoGIL Python means for machine learning
6:39
Inference Characteristics of Streaming Speech Recognition
Efficient NLP
Inference Characteristics of Streaming Speech Recognition
12:02
Voice Writer: AI Dictation for Novelists
Efficient NLP
Voice Writer: AI Dictation for Novelists
1:08
How to measure LLM writing quality when there is no right answer?
Efficient NLP
How to measure LLM writing quality when there is no right answer?
10:13
Train your own writing style with Voice Writer
Efficient NLP
Train your own writing style with Voice Writer
1:14
Training LLM to play chess using Deepseek GRPO reinforcement learning
Efficient NLP
Training LLM to play chess using Deepseek GRPO reinforcement learning
29:38
The Most Accurate Speech-to-text APIs in 2025
Efficient NLP
The Most Accurate Speech-to-text APIs in 2025
23:58
Structured Output from LLMs: Grammars, Regex, and State Machines
Efficient NLP
Structured Output from LLMs: Grammars, Regex, and State Machines
17:20
Speech LLMs: Models that listen and talk back
Efficient NLP
Speech LLMs: Models that listen and talk back
12:43
The Architecture of Chrome Extension Permissions
Efficient NLP
The Architecture of Chrome Extension Permissions
13:13
Voice Writer for Chrome
Efficient NLP
Voice Writer for Chrome
0:31
When is a Biased Estimator Better? A Look at Ratio Estimators
Efficient NLP
When is a Biased Estimator Better? A Look at Ratio Estimators
10:25
AI-generated text: Detection methods and countermeasures
Efficient NLP
AI-generated text: Detection methods and countermeasures
14:42
Residual Vector Quantization for Audio and Speech Embeddings
Efficient NLP
Residual Vector Quantization for Audio and Speech Embeddings
13:53
Introducing Voice Writer
Efficient NLP
Introducing Voice Writer
0:30
Can Whisper be used for real-time streaming ASR?
Efficient NLP
Can Whisper be used for real-time streaming ASR?
8:41
Top 10 most cited and influential papers in the history of NLP
Efficient NLP
Top 10 most cited and influential papers in the history of NLP
11:04
Basic facts about the Teochew language
Efficient NLP
Basic facts about the Teochew language
0:37
Fine-tuning Whisper to learn my Chinese dialect (Teochew)
Efficient NLP
Fine-tuning Whisper to learn my Chinese dialect (Teochew)
28:10
A better Hugging Face model search with OpenAI, RAG, pgvector
Efficient NLP
A better Hugging Face model search with OpenAI, RAG, pgvector
22:28
Speculative Decoding: When Two LLMs are Faster than One
Efficient NLP
Speculative Decoding: When Two LLMs are Faster than One
12:46
NLP Model Finder Tool
Efficient NLP
NLP Model Finder Tool
0:26
Fun Fact about Machine Translation
Efficient NLP
Fun Fact about Machine Translation
0:25
Exploring the 24 Areas of Natural Language Processing Research
Efficient NLP
Exploring the 24 Areas of Natural Language Processing Research
29:56
Rotary Positional Embeddings: Combining Absolute and Relative
Efficient NLP
Rotary Positional Embeddings: Combining Absolute and Relative
11:17
The KV Cache: Memory Usage in Transformers
Efficient NLP
The KV Cache: Memory Usage in Transformers
8:33
Quantization vs Pruning vs Distillation: Optimizing NNs for Inference
Efficient NLP
Quantization vs Pruning vs Distillation: Optimizing NNs for Inference
19:46
How is Beam Search Really Implemented?
Efficient NLP
How is Beam Search Really Implemented?
8:15
Non-Autoregressive and Shallow Decoding: Speeding up Translation
Efficient NLP
Non-Autoregressive and Shallow Decoding: Speeding up Translation
8:22
Which transformer architecture is best? Encoder-only vs Encoder-decoder vs Decoder-only models
Efficient NLP
Which transformer architecture is best? Encoder-only vs Encoder-decoder vs Decoder-only models
7:38