Nayana-cognitivelab/Nayana-OCRBench-final_en_append
收藏Hugging Face2024-11-17 更新2025-04-19 收录
下载链接:
https://hf-mirror.com/datasets/Nayana-cognitivelab/Nayana-OCRBench-final_en_append
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
- config_name: bn
features:
- name: image
dtype: image
- name: original_image
dtype: string
- name: region_id
dtype: int64
- name: bbox
struct:
- name: xmin
dtype: int64
- name: ymin
dtype: int64
- name: xmax
dtype: int64
- name: ymax
dtype: int64
- name: translated_text
dtype: string
- name: english_text
dtype: string
- name: text_type
dtype: string
- name: padding_applied
struct:
- name: top
dtype: int64
- name: left
dtype: int64
- name: right
dtype: int64
- name: bottom
dtype: int64
- name: text_stats
struct:
- name: char_length
dtype: int64
- name: width
dtype: int64
- name: height
dtype: int64
- name: aspect_ratio
dtype: float64
- name: source
dtype: string
- name: en_image
dtype: image
splits:
- name: train
num_bytes: 14740470.0
num_examples: 186
download_size: 14561198
dataset_size: 14740470.0
- config_name: gu
features:
- name: image
dtype: image
- name: original_image
dtype: string
- name: region_id
dtype: int64
- name: bbox
struct:
- name: xmin
dtype: int64
- name: ymin
dtype: int64
- name: xmax
dtype: int64
- name: ymax
dtype: int64
- name: translated_text
dtype: string
- name: english_text
dtype: string
- name: text_type
dtype: string
- name: padding_applied
struct:
- name: top
dtype: int64
- name: left
dtype: int64
- name: right
dtype: int64
- name: bottom
dtype: int64
- name: text_stats
struct:
- name: char_length
dtype: int64
- name: width
dtype: int64
- name: height
dtype: int64
- name: aspect_ratio
dtype: float64
- name: source
dtype: string
- name: en_image
dtype: image
splits:
- name: train
num_bytes: 14413783.0
num_examples: 186
download_size: 14239961
dataset_size: 14413783.0
- config_name: hi
features:
- name: image
dtype: image
- name: original_image
dtype: string
- name: region_id
dtype: int64
- name: bbox
struct:
- name: xmin
dtype: int64
- name: ymin
dtype: int64
- name: xmax
dtype: int64
- name: ymax
dtype: int64
- name: translated_text
dtype: string
- name: english_text
dtype: string
- name: text_type
dtype: string
- name: padding_applied
struct:
- name: top
dtype: int64
- name: left
dtype: int64
- name: right
dtype: int64
- name: bottom
dtype: int64
- name: text_stats
struct:
- name: char_length
dtype: int64
- name: width
dtype: int64
- name: height
dtype: int64
- name: aspect_ratio
dtype: float64
- name: source
dtype: string
- name: en_image
dtype: image
splits:
- name: train
num_bytes: 14631822.0
num_examples: 186
download_size: 14427537
dataset_size: 14631822.0
- config_name: kn
features:
- name: image
dtype: image
- name: original_image
dtype: string
- name: region_id
dtype: int64
- name: bbox
struct:
- name: xmin
dtype: int64
- name: ymin
dtype: int64
- name: xmax
dtype: int64
- name: ymax
dtype: int64
- name: translated_text
dtype: string
- name: english_text
dtype: string
- name: text_type
dtype: string
- name: padding_applied
struct:
- name: top
dtype: int64
- name: left
dtype: int64
- name: right
dtype: int64
- name: bottom
dtype: int64
- name: text_stats
struct:
- name: char_length
dtype: int64
- name: width
dtype: int64
- name: height
dtype: int64
- name: aspect_ratio
dtype: float64
- name: source
dtype: string
- name: en_image
dtype: image
splits:
- name: train
num_bytes: 15096520.0
num_examples: 186
download_size: 14908783
dataset_size: 15096520.0
- config_name: ml
features:
- name: image
dtype: image
- name: original_image
dtype: string
- name: region_id
dtype: int64
- name: bbox
struct:
- name: xmin
dtype: int64
- name: ymin
dtype: int64
- name: xmax
dtype: int64
- name: ymax
dtype: int64
- name: translated_text
dtype: string
- name: english_text
dtype: string
- name: text_type
dtype: string
- name: padding_applied
struct:
- name: top
dtype: int64
- name: left
dtype: int64
- name: right
dtype: int64
- name: bottom
dtype: int64
- name: text_stats
struct:
- name: char_length
dtype: int64
- name: width
dtype: int64
- name: height
dtype: int64
- name: aspect_ratio
dtype: float64
- name: source
dtype: string
- name: en_image
dtype: image
splits:
- name: train
num_bytes: 15522631.0
num_examples: 186
download_size: 15323410
dataset_size: 15522631.0
- config_name: mr
features:
- name: image
dtype: image
- name: original_image
dtype: string
- name: region_id
dtype: int64
- name: bbox
struct:
- name: xmin
dtype: int64
- name: ymin
dtype: int64
- name: xmax
dtype: int64
- name: ymax
dtype: int64
- name: translated_text
dtype: string
- name: english_text
dtype: string
- name: text_type
dtype: string
- name: padding_applied
struct:
- name: top
dtype: int64
- name: left
dtype: int64
- name: right
dtype: int64
- name: bottom
dtype: int64
- name: text_stats
struct:
- name: char_length
dtype: int64
- name: width
dtype: int64
- name: height
dtype: int64
- name: aspect_ratio
dtype: float64
- name: source
dtype: string
- name: en_image
dtype: image
splits:
- name: train
num_bytes: 14607593.0
num_examples: 186
download_size: 14426979
dataset_size: 14607593.0
- config_name: or
features:
- name: image
dtype: image
- name: original_image
dtype: string
- name: region_id
dtype: int64
- name: bbox
struct:
- name: xmin
dtype: int64
- name: ymin
dtype: int64
- name: xmax
dtype: int64
- name: ymax
dtype: int64
- name: translated_text
dtype: string
- name: english_text
dtype: string
- name: text_type
dtype: string
- name: padding_applied
struct:
- name: top
dtype: int64
- name: left
dtype: int64
- name: right
dtype: int64
- name: bottom
dtype: int64
- name: text_stats
struct:
- name: char_length
dtype: int64
- name: width
dtype: int64
- name: height
dtype: int64
- name: aspect_ratio
dtype: float64
- name: source
dtype: string
- name: en_image
dtype: image
splits:
- name: train
num_bytes: 14763645.0
num_examples: 186
download_size: 14596665
dataset_size: 14763645.0
- config_name: pa
features:
- name: image
dtype: image
- name: original_image
dtype: string
- name: region_id
dtype: int64
- name: bbox
struct:
- name: xmin
dtype: int64
- name: ymin
dtype: int64
- name: xmax
dtype: int64
- name: ymax
dtype: int64
- name: translated_text
dtype: string
- name: english_text
dtype: string
- name: text_type
dtype: string
- name: padding_applied
struct:
- name: top
dtype: int64
- name: left
dtype: int64
- name: right
dtype: int64
- name: bottom
dtype: int64
- name: text_stats
struct:
- name: char_length
dtype: int64
- name: width
dtype: int64
- name: height
dtype: int64
- name: aspect_ratio
dtype: float64
- name: source
dtype: string
- name: en_image
dtype: image
splits:
- name: train
num_bytes: 14729148.0
num_examples: 186
download_size: 14563291
dataset_size: 14729148.0
- config_name: ta
features:
- name: image
dtype: image
- name: original_image
dtype: string
- name: region_id
dtype: int64
- name: bbox
struct:
- name: xmin
dtype: int64
- name: ymin
dtype: int64
- name: xmax
dtype: int64
- name: ymax
dtype: int64
- name: translated_text
dtype: string
- name: english_text
dtype: string
- name: text_type
dtype: string
- name: padding_applied
struct:
- name: top
dtype: int64
- name: left
dtype: int64
- name: right
dtype: int64
- name: bottom
dtype: int64
- name: text_stats
struct:
- name: char_length
dtype: int64
- name: width
dtype: int64
- name: height
dtype: int64
- name: aspect_ratio
dtype: float64
- name: source
dtype: string
- name: en_image
dtype: image
splits:
- name: train
num_bytes: 15305836.0
num_examples: 186
download_size: 15119176
dataset_size: 15305836.0
- config_name: te
features:
- name: image
dtype: image
- name: original_image
dtype: string
- name: region_id
dtype: int64
- name: bbox
struct:
- name: xmin
dtype: int64
- name: ymin
dtype: int64
- name: xmax
dtype: int64
- name: ymax
dtype: int64
- name: translated_text
dtype: string
- name: english_text
dtype: string
- name: text_type
dtype: string
- name: padding_applied
struct:
- name: top
dtype: int64
- name: left
dtype: int64
- name: right
dtype: int64
- name: bottom
dtype: int64
- name: text_stats
struct:
- name: char_length
dtype: int64
- name: width
dtype: int64
- name: height
dtype: int64
- name: aspect_ratio
dtype: float64
- name: source
dtype: string
- name: en_image
dtype: image
splits:
- name: train
num_bytes: 14663017.0
num_examples: 186
download_size: 14466743
dataset_size: 14663017.0
configs:
- config_name: bn
data_files:
- split: train
path: bn/train-*
- config_name: gu
data_files:
- split: train
path: gu/train-*
- config_name: hi
data_files:
- split: train
path: hi/train-*
- config_name: kn
data_files:
- split: train
path: kn/train-*
- config_name: ml
data_files:
- split: train
path: ml/train-*
- config_name: mr
data_files:
- split: train
path: mr/train-*
- config_name: or
data_files:
- split: train
path: or/train-*
- config_name: pa
data_files:
- split: train
path: pa/train-*
- config_name: ta
data_files:
- split: train
path: ta/train-*
- config_name: te
data_files:
- split: train
path: te/train-*
---
提供机构:
Nayana-cognitivelab



