Artificial-Soul/Devika
image-to-text model by Artificial-Soul
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Devika is an open-source model for recognizing single handwritten Malayalam words from images. It is a fine-tuned version of Microsoft's trocr-large-handwritten with a new Malayalam character-level decoder vocabulary. Evaluated on the held-out test split (19,635 word images per the dataset description), which was never used for training or checkpoint selection. Word accuracy counts a word as correct only if every character matches, so a single wrong vowel sign or conjunct component fails the whole word. This is why it is much lower than character accuracy. Checkpoint selection. This release is the checkpoint at step 39,000 (about epoch 29), chosen by lowest validation CER: Validation CER, tracked every 1,000 steps, plateaued in the 1.7–2.1% range in the later epochs. The encoder and decoder transformer layers are initialized from the English TrOCR checkpoint. The decoder's embedding and output layers were resized and re-learned for the Malayalam character vocabulary, since the original English…
Read the full model card ↗ · Preview checked 2026-09-28T07:08:59.332Z
Inside the original model card — Document outline
- Devika: Malayalam Handwritten Word OCR
- Results
- Model details
- Training data
- Training procedure
- How to use
- Limitations
- Using Devika on full documents
- Intended use
- Licensing note
- Acknowledgements
- Citation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Artificial-Soul/Devika is a image-to-text model repository published by Artificial-Soul on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-to-text
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2026-09-28T05:52:10.000Z
- Last modified
- 2026-09-28T06:27:51.000Z
Compatibility and lineage
Reported languages: ml
Reported base models: microsoft/trocr-large-handwritten
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-28T06:38:00.545Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.