OpenNMT-py models - OpenNMT (original) (raw)

OpenNMT-py models

This page lists pretrained models for OpenNMT-py.

Translation
Summarization
- English
- Chinese
Dialog

Translation

| | 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 |

| | 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 = 31.2newstest2016 = 40.7newstest2017 = 32.9newstest2018 = 49.1newstest2019 = 45.9 |

| | English-German - v2 format model Transformer (download) | | | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Configuration | Base Transformer configuration with standard training options | | Data | WMT with shared SentencePiece modelOriginal Paper replication | | BLEU | newstest2014 = 26.89newstest2017 = 28.09 |

| | 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 |

Summarization

English

| | 2-layer LSTM (download) | | | ---------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- | | Configuration | 2-layer LSTM with hidden size 500 trained for 20 epochs | | Data | Gigaword standard | | Gigaword F-Score | R1 = 33.60R2 = 16.29RL = 31.45 |

| | 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 = 35.51R2 = 17.35RL = 33.17 |

| | Transformer (download) | | | ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- | | Configuration | See OpenNMT-py summarization example | | Data | CNN/Daily Mail |

Chinese

| | 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 = 35.67R2 = 23.06RL = 33.14 |

Dialog

| | 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 |