voxreality/nllb-asr-synthetic-robust-onnx

By voxreality · ↓ 3 · ♥ 0 · Updated 2025-04-29

What's in this repo

This page lists the files in voxreality/nllb-asr-synthetic-robust-onnx, including decoder_model.onnx, encoder_model.onnx.

2 ONNX models (.onnx files)
10 files, including 5 .json, 2 .onnx, 1 .md, 1 .model
Last updated 2025-04-29

ONNX files

File	Size	Download
decoder_model.onnx	—	Download
encoder_model.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

ONNX format of voxreality/nllb-asr-synthetic-robust model

Model inference example:

from transformers import AutoTokenizer
from optimum.onnxruntime import ORTModelForSeq2SeqLM

model_path = "voxreality/nllb-asr-synthetic-robust-onnx"
model = ORTModelForSeq2SeqLM.from_pretrained(model_path, use_cache=False)
tokenizer = AutoTokenizer.from_pretrained(model_path)

src_lang = 'eng_Latn'
tgt_lang = 'deu_Latn'

input_text = "This is a good day"

tokenizer.src_lang = src_lang
inputs = tokenizer(input_text, return_tensors='pt')
model_output = model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id[tgt_lang])
output_text = tokenizer.batch_decode(model_output, skip_special_tokens=True)[0]

print(output_text)

Model info

onnx m2m_100 license:apache-2.0 region:us

↓ 3 ♥ 0

Created: 2025-04-24

Updated: 2025-04-29

View on Hugging Face

Files (10)

.gitattributes

README.md

config.json

decoder_model.onnx ONNX

encoder_model.onnx ONNX

generation_config.json

sentencepiece.bpe.model

special_tokens_map.json

tokenizer.json

tokenizer_config.json

Related models

More models

No task type declared.