Image-to-Text
Transformers
Safetensors
Malayalam
vision-encoder-decoder
image-text-to-text
ocr
trocr
handwritten-text-recognition
malayalam
indic
Eval Results (legacy)
Instructions to use Artificial-Soul/devika_malayalam_trocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Artificial-Soul/devika_malayalam_trocr with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-text", model="Artificial-Soul/devika_malayalam_trocr")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Artificial-Soul/devika_malayalam_trocr") model = AutoModelForMultimodalLM.from_pretrained("Artificial-Soul/devika_malayalam_trocr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from Artificial-Soul/devika_malayalam_trocr: direct link, hf CLI and curl.
- Browser
- Download file 248 Bytes
-
https://huggingface.co/Artificial-Soul/devika_malayalam_trocr/resolve/main/generation_config.json
- Command line
-
hf download hf://Artificial-Soul/devika_malayalam_trocr/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/Artificial-Soul/devika_malayalam_trocr/resolve/main/generation_config.json
248 Bytes
| { | |
| "bos_token_id": 0, | |
| "decoder_start_token_id": 2, | |
| "early_stopping": true, | |
| "eos_token_id": 2, | |
| "max_length": 32, | |
| "no_repeat_ngram_size": 0, | |
| "num_beams": 5, | |
| "pad_token_id": 1, | |
| "transformers_version": "4.46.0", | |
| "use_cache": false | |
| } | |