Cluster 656999

7 repos

JavaScript · 2

Jupyter Notebook · 2

TypeScript · 2

Python · 1

automatic-speech-recognition ·0

benchmarks ·0

gpt-2 ·0

huggingface ·0

llm ·0

machine-learning ·0

natural-language-processing ·0

n-grams ·0

speech-recognition ·0

text-generation ·0

Related clusters

CTCycle/TKBEN-tokenizers-benchmarker

Explore and benchmark public and custom tokenizers from HuggingFace using different SOTA metrics

Python

558 commits

Likheet/tokenizer-lab

No description

TypeScript

13 commits

daaain/online-llm-tokenizer

No description

JavaScript

6 commits

lucaspanizio/ai-tokenizer

Demonstração interativa de como diferentes modelos de IA tokenizam texto.

TypeScript

3 commits

eordano/tokencount

Side-by-side text diff with token counts across different tokenizers. Also available as offline…

JavaScript

2 commits

Akshat4112/recipe-generator

German recipe generator web app powered by local GPT-2 — enter ingredients, get a recipe.

Jupyter Notebook

42 commits

andrea-gasparini/asr-lexical-semantic-error-correction-study

A study on Word Sense Disambiguation for lexical-semantic error correction in Speech Recognition.…

Jupyter Notebook

67 commits