This is an English-Deutsch machine translation model based on non-autoregressive Transformer topology.
Tokenization occurs using the SentencePieceBPETokenizer (see the demo code for implementation details) and the enclosed tokenizer_src and tokenizer_tgt folders.
| Metric | Value |
|---|---|
| GOps | 23.19 |
| MParams | 77.47 |
| Source framework | PyTorch* |
The quality metrics were calculated on the wmt19-en-de dataset ("test" split in lower case).
| Metric | Value |
|---|---|
| BLEU | 17.7 % |
Use accuracy_check [...] --model_attributes <path_to_folder_with_downloaded_model> to specify the path to additional model attributes. path_to_folder_with_downloaded_model is a path to the folder, where the current model is downloaded by Model Downloader tool.
name: tokens
shape: 1, 150
description: sequence of tokens (integer values) representing the tokenized sentence.
The sequence structure is as follows (<s>, </s> and <pad> should be replaced by corresponding token IDs as specified by the dictionary):
<s> + tokenized sentence + </s> + (<pad> tokens to pad to the maximum sequence length of 150)
name: pred
shape: 1, 200
description: sequence of tokens (integer values) representing the tokenized translation.
The sequence structure is as follows (<s>, </s> and <pad> should be replaced by corresponding token IDs as specified by the dictionary):
<s> + tokenized sentence + </s> + (<pad> tokens to pad to the maximum sequence length of 150)
The model can be used in the following demos provided by the Open Model Zoo to show its capabilities:
[*] Other names and brands may be claimed as the property of others.