| --- |
| language: |
| - en |
| - tr |
| license: cc-by-nc-2.0 |
| library_name: transformers |
| pipeline_tag: translation |
| tags: |
| - translation |
| - marian |
| - english |
| - turkish |
| base_model: Helsinki-NLP/opus-mt-tc-big-en-tr |
| --- |
| |
| # NedoTranslator |
|
|
| NedoTranslator is an English-to-Turkish machine translation model fine-tuned from |
| Helsinki-NLP/opus-mt-tc-big-en-tr at base revision |
| e539fc16a8a1a0ea5950eb339b595bfcce990e90. |
|
|
| ## Model details |
|
|
| - Task: English to Turkish machine translation |
| - Architecture: MarianMT |
| - Parameters: 236,883,968 |
| - Checkpoint dtype: float32 |
| - Recommended decoding for benchmark parity: beam search with num_beams=4 |
| - License: CC BY 4.0, following the base model license |
| |
| ## Usage |
| |
| ~~~python |
| from transformers import AutoModelForSeq2SeqLM, AutoTokenizer |
| |
| model_id = "nmsofficial/NedoTranslator" |
| tokenizer = AutoTokenizer.from_pretrained(model_id) |
| model = AutoModelForSeq2SeqLM.from_pretrained(model_id) |
|
|
| text = "Artificial intelligence is changing the way software is built." |
| inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512) |
| outputs = model.generate(**inputs, num_beams=4, max_new_tokens=256) |
| print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
| ~~~ |
| |
| ## Provenance |
| |
| This Hub release corresponds to the local NedoTranslator production v1 checkpoint |
| used in the September 2026 EN-to-TR benchmark runs. The uploaded bundle contains only |
| the standard Transformers inference assets and excludes cluster-specific paths, |
| training manifests, and local benchmark artifacts. |
| |
| Model weights SHA-256: |
| 0344f97adf437f4aaa5cd63da05d4fa5a59bbab483c25165d37fecf7e799a5f5 |
| |
| ## Attribution |
| |
| Base model: Helsinki-NLP, opus-mt-tc-big-en-tr. |
| Please retain attribution and follow the CC BY 4.0 license terms when redistributing |
| or adapting this model. |
