Translation
Transformers
Safetensors
Kannada
English
controlmt
text2text-generation
machine-translation
kannada
english
indic
low-resource
code-mix
encoder-decoder
custom_code
Eval Results (legacy)
Instructions to use anandkaman/controlmt-v2.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anandkaman/controlmt-v2.3 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" 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("translation", model="anandkaman/controlmt-v2.3", trust_remote_code=True)# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("anandkaman/controlmt-v2.3", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Release Eval Report — flores_devtest
- ckpt:
checkpoints_v23/step_255000.pt - beam: 6 | anti_lm_alpha: 0.5
- style kn→en: natural | style en→kn: natural
- test pairs: 1012
Aggregate scores
| Metric | KN→EN | EN→KN |
|---|---|---|
| CometKiwi (no ref) | 0.8437 | 0.8663 |
| COMET-DA (with ref) | 0.8459 | 0.8443 |
| BLEU | 27.20 | 18.50 |
| chrF | 55.84 | 56.12 |
Targets (CONTROLMT.md Section 10.1)
- COMET-DA ship floor ≥ 0.82 / aspirational 0.85
- CometKiwi ship floor ≥ 0.75 / aspirational 0.80