一个可以验证和计算文本消耗 Token 的小工具,支持在浏览器中使用,汉化自 OpenAI Tokenizer。
-
Updated
May 13, 2024 - Go
一个可以验证和计算文本消耗 Token 的小工具,支持在浏览器中使用,汉化自 OpenAI Tokenizer。
Production-grade token counter for PDF, TXT, DOCX, MD, and PPTX files using real GPT tokenization via tiktoken. Features streaming extraction, constant-memory processing, OCR/scanned PDF detection, batch processing, and Hugging Face Spaces-ready Gradio UI.
Add a description, image, and links to the token-calc topic page so that developers can more easily learn about it.
To associate your repository with the token-calc topic, visit your repo's landing page and select "manage topics."