How audio becomes tokens

I am currently working on training an Automatic Speech Recognition (ASR) model for Nepali, and this is the first of three posts on it.

Aug 20 • Shreeya

1

July 2026

Benchmark and Resource Gaps for Nepali Speech Tasks

Even with the breakthroughs in Large Language Models (LLMs) there are significant performance gaps in Natural Language Processing (NLP) systems for…

Jul 22 • Shreeya

3

March 2025

Low-Resource NLP in the Era of LLMs - Introduction

There has, undoubtedly, been drastic shifts in the landscape of Natural Language Processing (NLP) research and development with the breakthrough of…

Mar 1, 2025 • Shreeya

4

1

January 2025

Do LLMs Engage in True Reasoning?

Can LLMs “truly” reason?

Jan 30, 2025 • Shreeya

6

September 2024

Strawberry (o1) - Does changing language affect its reasoning?

What is going on inside OpenAI's o1 model and if changing language affect its reasoning - a short bilingual experiment.

Sep 22, 2024 • Shreeya

3

1

Low-Rank Adaptation of LLaMA 3 for Nepali and Hindi

PEFT Techniques and Findings from Fine-tuning LLaMA 3 with Low-Rank Adaptation for Nepali and Hindi

Sep 5, 2024 • Shreeya

4

1

July 2024

Aligning LLMs - Fine-Tuning LLaMA with SFT and RHLF

Part 3: Understanding LLM alignment with Supervised Fine-Tuning and Reinforcement Learning from Human Feedback

Jul 4, 2024 • Shreeya

3

1

1

June 2024

Large Language Models - A Curated Reading List

While I am working on the blog series on the LLaMA family of models, I have also put together a curated reading list of papers that chart the evolution…

Jun 16, 2024 • Shreeya

5

May 2024

Whose Weights and Biases?

Who decides how AI thinks and behaves?

May 19, 2024 • Shreeya

2

The LLaMA Family of Models, Model Architecture, Size, and Scaling Laws

Part 2: A look into the Meta's LLaMA family of models before we deep-dive into each components from multi-lingual lens

May 5, 2024 • Shreeya

3

April 2024

Exploring multilingual aspects and vocabulary of LLaMA 3 compared to LLaMA 2

This is the first part of a series where I will discuss the multilingual abilities of the LLaMA 3 model.

Apr 22, 2024 • Shreeya

2

March 2024

The Cost of Ideas

While proofreading the "How LLMs Break Down Language from Text to Tokens" section from my last blog, Nolan asked me a thought-provoking question: "Then…

Mar 30, 2024 • Shreeya and Nolan Kramer

2