translate-en-tdt
Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-en-tdt
Machine translation model, en to tdt, published by Windstorm Labs.
Attribution
Derived from Helsinki-NLP/opus-mt-en-tdt, licensed apache-2.0.
Windstorm Labs did not train the original model. This notice provides the attribution the
licence requires.
What was changed
The weights in this repository have been modified from the original. A LoRA fine-tune trained on parallel corpus data and merged into the base weights.
| Method | windy-hallmark |
| Tensors modified | 36 of 254 |
| Max absolute weight delta | 7.034e-05 |
| Verified | tensor-by-tensor against the upstream original, 2026-07-26 |
The comparison is tensor-level rather than file-level: safetensors and PyTorch .bin
containers hash differently even when the tensors inside are identical, so a file-hash
mismatch would prove nothing.
Contents
A single transformers build in safetensors format, loadable directly:
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tok = AutoTokenizer.from_pretrained("WindyTranslate/translate-en-tdt")
model = AutoModelForSeq2SeqLM.from_pretrained("WindyTranslate/translate-en-tdt")
batch = tok(["<your text here>"], return_tensors="pt", padding=True)
print(tok.batch_decode(model.generate(**batch), skip_special_tokens=True))
Other builds of this pair, including CTranslate2 INT8, are not included in this repository.
Limitations
- A single language direction:
entotdt. - Not yet scored for quality. Language-verified with GlotLID (verdict: MATCH): the output is in the claimed language. That is not a quality score. The weights are verified to differ from the original; that is a statement about provenance, not about translation quality.
- Quality is not monotonic with model size or with the amount of fine-tuning applied.