-
# Overview
The goal is to add support for efficient batch processing of inputs to the MLX-VLM library. This will allow users to process multiple images and text prompts simultaneously to generate cor…
-
Follow-on from #17, #22, #25. Add a `PdfParagraph` object that allows for easier handling of multi-line text with embedded character formatting changes.
Ideally, it would be possible to generate a …
-
#### Problem Description:
While processing a large number of images (approximately 1000) using RapidOCR, I encountered the following errors midway through the process:
1. **Leaked Semaphore Object…
-
Hi
I didn't have this problem before when i installed k2 with conda
I have recently cloned and compiled directly from sources, and I have this problem in reading fst (created by kaldilm)
k2/bui…
-
The ability to see what was changed from the previous to the current revision could increase the efficiency during the review process. For example: After a document was already reviewed and accepted b…
-
UnicodeEncodeError: 'gbk' codec can't encode character '\U0001f3ac' in position 0: illegal multibyte sequence
Traceback:
File "D:\miniconda3\envs\videolingo\lib\site-packages\streamlit\runtime\scrip…
-
**Environment:**
- VLLM Version: v0.2.7
- HF Version: 4.37.0
- Model Used: teknium/OpenHermes-2.5-Mistral-7B
- Python Version: 3.10.13
- Operating System: Linux-5.10.201-191.748.amzn2.x86_64-x86_…
-
The `rich.progress` module provides progress bars for stdout. However, the result is not displayed until after the progress bar is complete which defeats the point.
I've tried many of the examples i…
-
Most of the time lectures are given in either PDF/ ppt/ notes(taken in txt). Currently we have pdf as acceptable file processing format. Can improve this by providing PPT or text input processing as w…
-
pull request에 올려놓은 것처럼 전처리를 총 4 단계로 분리하여 성능비교를 해보았습니다.
> 0: remove_special_char, 독일어, 사우디어, 라틴어 제거
> 1: substitution_special_char, 특수문자 제거
> 2: substitution_date, 기간 표시 수정 '-' => '~' (ex: 122…