Tools,

EasyOCR, tested on a Mac

1,658 of 1,955

words found, 10 scanned pages

Get the script

Run EasyOCR on a scanned PDF

58 to 61 s for 10 pages, Mac GPU

98 MB of models, first run

On a Mac, in a folder with scan.pdf:

python3 -m venv eo && source eo/bin/activate
pip install easyocr pypdfium2
python ocr.py scan.pdf > scan.txt

ocr.py:

import sys
import easyocr
import numpy as np
import pypdfium2 as pdfium

reader = easyocr.Reader(["en"], verbose=False)
for page in pdfium.PdfDocument(sys.argv[1]):
    img = np.array(page.render(scale=300 / 72).to_pil().convert("L"))
    print("\n".join(reader.readtext(img, detail=0, paragraph=True)))

EasyOCR reads images, not PDFs, so pypdfium2 draws each page at 300 dpi. Once the models are downloaded, a run with no network gave the same text.

gpu=True already means the Mac GPU

Reader(["en"]) has gpu=True by default. With no CUDA, EasyOCR 1.7.2 picks MPS, the Apple GPU.

Seconds for the 10 JPEG files
Mode Mac GPU CPU, 2 threads
readtext defaults 42.8 s 338.6 s
paragraph=True 39.4 s 368.5 s

quantize=False on 2 CPU threads: same text, 353.3 s. Other jobs shared the Mac, so times are rough.

Every run, CPU too, prints a torch pin_memory warning. GPU and CPU text matched, byte for byte.

paragraph=True: most words

On the 10 JPEG files, Mac GPU. Every row after the first also has paragraph=True.

Of 1,955 words
Option Words found Time
defaults (short text boxes) 1,606 42.8 s
paragraph=True 1,670 39.4 s
+ mag_ratio=1.5 1,670 (same text) 58.3 s
+ batch_size=8 1,670 42.1 s
+ text_threshold=0.5, low_text=0.3 1,650 53.4 s
+ decoder="beamsearch" 1,550 56.9 s

The page script also passes detail=0, which returns only the strings. From the PDF it found 1,658: the two image paths differ a little.

Models land in ~/.EasyOCR/model

The first Reader(["en"]) downloads them from the JaidedAI/EasyOCR GitHub releases. That run took 64.1 s. Later runs downloaded nothing.

File Size Job
craft_mlt_25k.pth 83.2 MB finds text
english_g2.pth 15.1 MB reads English

model_storage_directory picks another folder. With download_enabled=False and no models:

FileNotFoundError: Missing ~/.EasyOCR//model/craft_mlt_25k.pth and downloads disabled

The real message shows your full home folder in place of ~.

The progress bar lands in your text file

With verbose left on, the first Reader(["en"]) printed 11,147 progress-bar updates into stdout, and the first line of text came right after the last one. So > scan.txt caught them all.

verbose=False, as in the script, gave 0.

Two errors you will hit

A PDF path in place of an image:

OSError: Could not find a backend to open `scan.pdf`` with iomode `r`.

Draw the pages with pypdfium2, as in the script.

Reader(["ch_sim", "ja"]) stops before it downloads a Chinese or Japanese model:

ValueError: Chinese_sim is only compatible with English, try lang_list=["ch_sim","en"]

Keep the CRAFT detector, not dbnet18

detect_network="dbnet18" fails on the GPU:

TypeError: Cannot convert a MPS Tensor to float64 dtype as the MPS framework doesn't support float64. Please use float32 instead.

On the CPU, it fails when ninja is not on PATH, for example when you run eo/bin/python without activating the venv:

RuntimeError: Input type is cpu, but 'deform_conv_cpu.*.so' is not imported successfully.

With the venv active, it builds C++ code and downloads 46.8 MB more. Then it finds fewer words, more slowly:

2 CPU threads, paragraph=True, of 1,955 words
Detector Words found Time
CRAFT (default) 1,670 368.5 s
dbnet18 1,468 788.0 s

EasyOCR often reads s as g

Same 10 pages, same scorer, of 1,955 words
Reader Words found
Gemma 4 e4b 1,947
RapidOCR 1,894
The pdf-ocr Actor's code 1,879
Tesseract 5.5.4 1,878
EasyOCR, paragraph=True 1,670

In the page script's text (1,658 words found), 113 words came out as another word.

Of those, 27 are an s read as g or 8, as in glackened, gtory and a8. Most others are punctuation:

How I tested it
  • Pages: the 10 scans of OCR in n8n, proofread Wikisource book pages, 1,955 true words, as 1920 px JPEGs and one PDF.
  • easyocr 1.7.2 and torch 2.15.0 on Python 3.14.7, on an Apple Silicon Mac. Installing easyocr and pypdfium2 made a venv of 1,111 MB.
  • One run at a time, lowest priority, torch on 2 CPU threads. The first run started from an empty model folder.
  • Score: true words found in order. The Gemma 4, Tesseract and Actor rows come from my Gemma 4 test of the same files, RapidOCR from my RapidOCR test.
  • batch_size=8 changed the text a little: 17 paragraphs, not 20.
What I did not test
  • CUDA and NVIDIA GPUs, Windows and Linux.
  • Other languages, and text boxes (the default detail=1).
Sources

Text from a PDF, no model download

Run it yourself. Our Apify Actor takes a PDF and returns text, with no model download on your Mac. Its code found 1,879 of these 1,955 words.

Try the Actor

Or send us the scan. Tack, our AI, does the job for $29, up to 50 pages. First page free.

Get one page free

Questions people ask

Does EasyOCR use the GPU on a Mac?

Yes, by default: gpu=True picks MPS, the Apple GPU. With paragraph=True it took 39.4 s on the GPU and 368.5 s on 2 CPU threads, with the same text.

Where does EasyOCR store its models?

In ~/.EasyOCR/model. For English that is craft_mlt_25k.pth (83.2 MB), which finds the text, and english_g2.pth (15.1 MB), which reads it.

Is EasyOCR better than Tesseract?

Not on these scanned book pages. EasyOCR found 1,670 of 1,955 words on the JPEG files (1,658 with the page script), and Tesseract 5.5.4 found 1,878.