extracted text is weird

#4
by revivedbeast - opened

due to unset params? Any advice is appreciated. Thanks.
Here is the code for extracting text from an image -

model = AutoModelForImageTextToText.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf", device_map=device)
processor = AutoProcessor.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf")

image = Image.open("image_2017.png")
inputs = processor(image, return_tensors="pt", format=True).to(device)

generate_ids = model.generate(
**inputs,
do_sample=False,
tokenizer=processor.tokenizer,
stop_strings="<|im_end|>",
max_new_tokens=4096,
)

generated = processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print("Generated: \n\n", generated)

Sign up or log in to comment