aina-translator-es-ast-onnx

ONNX export of projecte-aina/aina-translator-es-ast, Projecte Aina's (Barcelona Supercomputing Center, Language Technologies Unit) Spanish → Asturian machine translation model. All credit for training data, fine-tuning and evaluation goes to Projecte Aina — see the source model card for training details and evaluation numbers.

Asturian has almost no other machine-translation coverage, which is why this export exists: to make the model runnable with onnxruntime (CPU, no PyTorch/CUDA dependency) via optimum.

Licence

cc-by-nc-4.0, verbatim as declared on the source model card (projecte-aina/aina-translator-es-ast). Same licence applies to this derived ONNX export.

Files

encoder_model.onnx(_data)              fp32 encoder
decoder_model.onnx(_data)              fp32 decoder (no cache)
decoder_with_past_model.onnx(_data)    fp32 decoder (with KV cache)
int8/encoder_model.onnx(_data)         dynamic-quantized (uint8) encoder
int8/decoder_model.onnx(_data)         dynamic-quantized (uint8) decoder
int8/decoder_with_past_model.onnx(_data) dynamic-quantized (uint8) decoder w/ cache
sentencepiece.bpe.model, tokenizer.json, tokenizer_config.json, ...  tokenizer files (NLLB-style SentencePiece)

fp32 total: ~6.9 GB. int8 total: ~1.8 GB.

Weights are stored as external data (*.onnx_data next to each *.onnx graph file — note the underscore, not a dot, which is what transformers/optimum expect when loading from the Hub).

Export

Base architecture: M2M100ForConditionalGeneration (transformers model_type: m2m_100), fine-tuned by Projecte Aina from facebook/nllb-200-distilled-600M.

optimum-cli export onnx \
  --model projecte-aina/aina-translator-es-ast \
  --task text2text-generation-with-past \
  --no-post-process \
  aina-translator-es-ast-onnx

--no-post-process is required: optimum's decoder-merge step OOMs on this model size on constrained hardware. As a result the ONNX export ships an un-merged decoder_model.onnx (no cache) and decoder_with_past_model.onnx (with cache) instead of a single decoder_model_merged.onnx.

int8 dynamic quantization (onnxruntime.quantization.quantize_dynamic, QUInt8 weights) was applied to each of the three graphs.

Target-language mechanism

Single-direction fine-tune: Spanish → Asturian only, no target forcing needed at inference time. The tokenizer's tokenizer_config.json fixes src_lang: spa_Latn, tgt_lang: ast_Latn — this is the real NLLB-200 Asturian tag (unlike the Aranese/Occitan sibling model, which needed a new custom tag). There is no forced_bos_token_id in generation_config.json; a plain tokenizer(text) + model.generate() call already yields Asturian output — the fixed tgt_lang plus decoder_start_token_id (2) are sufficient.

Parity

8 held-out Spanish sentences, num_beams=4, max_new_tokens=64, compared against the original PyTorch model (transformers.AutoModelForSeq2SeqLM) with identical decoding settings.

	exact-match rate
ONNX fp32	8/8 = 100.0%
ONNX int8 (dynamic)	7/8 = 87.5%

(The one int8 divergence was a fluent paraphrase, not a wrong-language or garbled output: "¿Cómo ta?" vs "¿Cuál ye'l to estáu?" for "¿cómo estás?".)

Sample translations observed (es → ast):

Spanish	Asturian
Hola, ¿cómo estás?	Hola, ¿cuál ye'l to estáu?
El tiempo hoy es muy bueno.	El tiempu güei ye mui bonu.
Me gustaría reservar una mesa para dos personas.	Gustaríame reservar una mesa pa dos persones.
¿Dónde está la estación de tren?	¿Onde ta la estación de tren?
Este libro es muy interesante.	Esti llibru ye perinteresante.
Los niños juegan en el parque.	Los neños xueguen nel parque.
Necesito ayuda con mi ordenador.	Faime falta ayuda col mio ordenador.
La reunión comenzará a las diez de la mañana.	La xunta entamará a les diez de la mañana.

Usage

from transformers import AutoTokenizer
from optimum.onnxruntime import ORTModelForSeq2SeqLM

model_id = "TigreGotico/aina-translator-es-ast-onnx"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = ORTModelForSeq2SeqLM.from_pretrained(model_id)  # fp32
# int8: ORTModelForSeq2SeqLM.from_pretrained(model_id, subfolder="int8")

text = "Hola, ¿cómo estás?"
ids = tokenizer(text, return_tensors="pt").input_ids
out = model.generate(ids, num_beams=4, max_new_tokens=64)
print(tokenizer.decode(out[0], skip_special_tokens=True))
# Hola, ¿cuál ye'l to estáu?

Attribution

All modeling and training work is by Projecte Aina (Language Technologies Unit, Barcelona Supercomputing Center) — this repository only republishes an ONNX conversion of their weights for offline/CPU inference. Source model: projecte-aina/aina-translator-es-ast. Contact for the original model: langtech@bsc.es.