| layout | title |
|---|---|
page |
OpenNMT-py models |
This page lists pretrained models for OpenNMT-py.
- TOC {:toc}
{:.pretrained} | | New! NLLB 200 3.3B - Transformer (download) | | | New! NLLB 200 1.3B - Transformer (download) | | | New! NLLB 200 1.3B distilled - Transformer (download) |
| New! NLLB 200 600M - Transformer (download) | |
|---|---|
| Configuration | Yaml file example to run inference inference config Please change the source and terget languages in the yaml |
| Sentence Piece model | SP Model |
| Results | cf Forum |
{:.pretrained}
| New! v3 English-German - Transformer Large (download) | |
|---|---|
| BPE Model | BPE '{"mode": "aggressive", "joiner_annotate": True, "preserve_placeholders": True, "case_markup": True, "soft_case_regions": True, "preserve_segmented_tokens": True, "segment_case": True, "segment_numbers": True, "segment_alphabet_change": True}' |
| BLEU | newstest2014 = 31.2 newstest2016 = 40.7 newstest2017 = 32.9 newstest2018 = 49.1 newstest2019 = 45.9 |
{:.pretrained}
| English-German - v2 format model Transformer (download) | |
|---|---|
| Configuration | Base Transformer configuration with standard training options |
| Data | WMT with shared SentencePiece model Original Paper replication |
| BLEU | newstest2014 = 26.89 newstest2017 = 28.09 |
{:.pretrained}
| German-English - 2-layer BiLSTM (download) | |
|---|---|
| Configuration | 2-layer BiLSTM with hidden size 500 trained for 20 epochs |
| Data | IWSLT '14 DE-EN |
| BLEU | 30.33 |
{:.pretrained}
| 2-layer LSTM (download) | |
|---|---|
| Configuration | 2-layer LSTM with hidden size 500 trained for 20 epochs |
| Data | Gigaword standard |
| Gigaword F-Score | R1 = 33.60 R2 = 16.29 RL = 31.45 |
{:.pretrained}
| 2-layer LSTM with copy attention (download) | |
|---|---|
| Configuration | 2-layer LSTM with hidden size 500 and copy attention trained for 20 epochs |
| Data | Gigaword standard |
| Gigaword F-Score | R1 = 35.51 R2 = 17.35 RL = 33.17 |
{:.pretrained}
| Transformer (download) | |
|---|---|
| Configuration | See OpenNMT-py summarization example |
| Data | CNN/Daily Mail |
{:.pretrained}
| 1-layer BiLSTM (download) | |
|---|---|
| Configuration | See OpenNMT-py summarization example |
| Data | CNN/Daily Mail |
| Gigaword F-Score | R1 = 39.12 R2 = 17.35 RL = 36.12 |
{:.pretrained}
| 1-layer BiLSTM (download) | |
|---|---|
| Author | playma |
| Configuration | Preprocessing options: src_vocab_size 8000, tgt_vocab_size 8000, src_seq_length 400, tgt_seq_length 30, src_seq_length_trunc 400, tgt_seq_length_trunc 100. Training options: 1 layer, LSTM 300, WE 500, encoder_type brnn, input feed, AdaGrad, adagrad_accumulator_init 0.1, learning_rate 0.15, 30 epochs |
| Data | LCSTS |
| Gigaword F-Score | R1 = 35.67 R2 = 23.06 RL = 33.14 |
{:.pretrained}
| 2-layer LSTM (download) | |
|---|---|
| Configuration | 2 layers, LSTM 500, WE 500, input feed, dropout 0.2, global_attention mlp, start_decay_at 7, 13 epochs |
| Data | OpenSubtitles |