initial commit
Browse files- README.md +69 -0
- config.json +44 -0
- generation_config.json +16 -0
- metadata.json +1 -0
- pytorch_model.bin +3 -0
- source.spm +0 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +13 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- nb
|
5 |
+
- nn
|
6 |
+
|
7 |
+
tags:
|
8 |
+
- translation
|
9 |
+
|
10 |
+
license: apache-2.0
|
11 |
+
---
|
12 |
+
|
13 |
+
### eng-nor
|
14 |
+
|
15 |
+
* source language name: English
|
16 |
+
* target language name: Norwegian
|
17 |
+
* OPUS readme: [README.md](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nor/README.md)
|
18 |
+
|
19 |
+
* model: transformer-align
|
20 |
+
* source language code: en
|
21 |
+
* target language codes: nb, nn
|
22 |
+
* dataset: opus with backtranslations
|
23 |
+
* release date: 2021-04-20
|
24 |
+
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
|
25 |
+
* download original weights: [opus+bt-2021-04-20.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nor/opus+bt-2021-04-20.zip/eng-nor/opus+bt-2021-04-20.zip)
|
26 |
+
* a sentence-initial language token is required in the form of >>id<<(id = valid, usually three-letter target language ID)
|
27 |
+
* Training data:
|
28 |
+
* eng-nno: Tatoeba-train (1661769) wikipedia.aa.nno-eng (995603) wikipedia.ab.nno-eng (605107) wikiquote.aa.nno-eng (22626)
|
29 |
+
* eng-nob: Tatoeba-train (11525999) wikibooks.aa.nob-eng (37901) wikinews.aa.nob-eng (8706) wikipedia.aa.nob-eng (992563) wikipedia.ab.nob-eng (992772) wikipedia.ac.nob-eng (992621) wikipedia.ad.nob-eng (992828) wikipedia.ae.nob-eng (992812) wikipedia.af.nob-eng (976715) wikiquote.aa.nob-eng (10443) wikisource.aa.nob-eng (279891)
|
30 |
+
* Validation data:
|
31 |
+
* eng-nno: Tatoeba-dev, 505
|
32 |
+
* eng-nob: Tatoeba-dev, 5189
|
33 |
+
* total-size-shuffled: 1505
|
34 |
+
* devset-selected: top 1505 lines of Tatoeba-dev.src.shuffled
|
35 |
+
* Test data:
|
36 |
+
* Tatoeba-test.eng-nno: 460/3428
|
37 |
+
* Tatoeba-test.eng-nob: 4539/36110
|
38 |
+
* Tatoeba-test.eng-nor: 4999/39547
|
39 |
+
* test set translations file: [test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nor/opus+bt-2021-04-20.zip/eng-nor/opus+bt-2021-04-20.test.txt)
|
40 |
+
* test set scores file: [eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nor/opus+bt-2021-04-20.zip/eng-nor/opus+bt-2021-04-20.eval.txt)
|
41 |
+
* BLEU-scores
|
42 |
+
|Test set|score|
|
43 |
+
|---|---|
|
44 |
+
|Tatoeba-test.eng-nob|56.4|
|
45 |
+
|Tatoeba-test.eng-nor|55.4|
|
46 |
+
|Tatoeba-test.eng-nno|40.3|
|
47 |
+
* chr-F-scores
|
48 |
+
|Test set|score|
|
49 |
+
|---|---|
|
50 |
+
|Tatoeba-test.eng-nob|0.716|
|
51 |
+
|Tatoeba-test.eng-nor|0.71|
|
52 |
+
|Tatoeba-test.eng-nno|0.615|
|
53 |
+
|
54 |
+
### System Info:
|
55 |
+
* hf_name: eng-nor
|
56 |
+
* source_languages: en
|
57 |
+
* target_languages: nb,nn
|
58 |
+
* opus_readme_url: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nor/opus+bt-2021-04-20.zip/README.md
|
59 |
+
* original_repo: Tatoeba-Challenge
|
60 |
+
* tags: ['translation']
|
61 |
+
* languages: ['en', 'nb', 'nn']
|
62 |
+
* src_constituents: ['eng']
|
63 |
+
* tgt_constituents: ['nob', 'nno']
|
64 |
+
* src_multilingual: False
|
65 |
+
* tgt_multilingual: True
|
66 |
+
* helsinki_git_sha: 59400fea592520766f9910390155681bc930dbc4
|
67 |
+
* transformers_git_sha: fd5cdaeea6eafac32e9d967327bfa3dc0e0d962d
|
68 |
+
* port_machine: DESKTOP-6CPR2HH
|
69 |
+
* port_time: 2023-01-23-21:07
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "swish",
|
4 |
+
"architectures": [
|
5 |
+
"MarianMTModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bad_words_ids": [
|
9 |
+
[
|
10 |
+
54214
|
11 |
+
]
|
12 |
+
],
|
13 |
+
"bos_token_id": 0,
|
14 |
+
"d_model": 512,
|
15 |
+
"decoder_attention_heads": 8,
|
16 |
+
"decoder_ffn_dim": 2048,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 54214,
|
20 |
+
"decoder_vocab_size": 54215,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 8,
|
23 |
+
"encoder_ffn_dim": 2048,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 40041,
|
27 |
+
"forced_eos_token_id": 40041,
|
28 |
+
"init_std": 0.02,
|
29 |
+
"is_encoder_decoder": true,
|
30 |
+
"max_length": 512,
|
31 |
+
"max_position_embeddings": 512,
|
32 |
+
"model_type": "marian",
|
33 |
+
"normalize_embedding": false,
|
34 |
+
"num_beams": 6,
|
35 |
+
"num_hidden_layers": 6,
|
36 |
+
"pad_token_id": 54214,
|
37 |
+
"scale_embedding": true,
|
38 |
+
"share_encoder_decoder_embeddings": true,
|
39 |
+
"static_position_embeddings": true,
|
40 |
+
"torch_dtype": "float16",
|
41 |
+
"transformers_version": "4.26.0.dev0",
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 54215
|
44 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bad_words_ids": [
|
4 |
+
[
|
5 |
+
54214
|
6 |
+
]
|
7 |
+
],
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"decoder_start_token_id": 54214,
|
10 |
+
"eos_token_id": 40041,
|
11 |
+
"forced_eos_token_id": 40041,
|
12 |
+
"max_length": 512,
|
13 |
+
"num_beams": 6,
|
14 |
+
"pad_token_id": 54214,
|
15 |
+
"transformers_version": "4.26.0.dev0"
|
16 |
+
}
|
metadata.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"hf_name": "eng-nor", "source_languages": "en", "target_languages": "nb,nn", "opus_readme_url": "https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nor/opus+bt-2021-04-20.zip/README.md", "original_repo": "Tatoeba-Challenge", "tags": ["translation"], "languages": ["en", "nb", "nn"], "src_constituents": ["eng"], "tgt_constituents": ["nob", "nno"], "src_multilingual": false, "tgt_multilingual": true, "helsinki_git_sha": "59400fea592520766f9910390155681bc930dbc4", "transformers_git_sha": "fd5cdaeea6eafac32e9d967327bfa3dc0e0d962d", "port_machine": "DESKTOP-6CPR2HH", "port_time": "2023-01-23-21:07"}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8daa0ddf104081a4e798e59aa451b152525f48efc43aae55f6fea2ca959e5f82
|
3 |
+
size 199500873
|
source.spm
ADDED
Binary file (796 kB). View file
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
target.spm
ADDED
Binary file (783 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"model_max_length": 512,
|
4 |
+
"name_or_path": "marian_ckpt/eng-nor",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"separate_vocabs": false,
|
7 |
+
"source_lang": "eng",
|
8 |
+
"sp_model_kwargs": {},
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"target_lang": "nor",
|
11 |
+
"tokenizer_class": "MarianTokenizer",
|
12 |
+
"unk_token": "<unk>"
|
13 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|