✅ [KESİN ONAY] opus-mt-tc-big-gmq-en - Tüm hatalar giderildi ve mühürlendi.

opus-mt-tc-big-gmq-en/README.md

@@ -1,12 +1,166 @@
----
+  - mult
 language:
-- gmq
-- en
+  - "da"
+  - "en"
+  - "fo"
+  - "gmq"
+  - "is"
+  - "nb"
+  - "nn"
+  - "false"
+  - "sv"
 tags:
-- translation
-- marian
---- 
-
+  - "translation"
+  - "opusmttc"
+license: cc-by-4.0
+model-index:
+  - "name: opusmttcbiggmqen"
+  results:
+  - "task:"
+      name: Translation dan-eng
+      type: translation
+      args: dan-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: dan eng devtest
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 49.3
+  - "task:"
+      name: Translation isl-eng
+      type: translation
+      args: isl-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: isl eng devtest
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 34.2
+  - "task:"
+      name: Translation nob-eng
+      type: translation
+      args: nob-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: nob eng devtest
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 44.2
+  - "task:"
+      name: Translation swe-eng
+      type: translation
+      args: swe-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: swe eng devtest
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 49.8
+  - "task:"
+      name: Translation isl-eng
+      type: translation
+      args: isl-eng
+    dataset:
+      name: newsdev2021.is-en
+      type: newsdev2021.is-en
+      args: isl-eng
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 30.4
+  - "task:"
+      name: Translation dan-eng
+      type: translation
+      args: dan-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba
+      args: dan-eng
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 65.9
+  - "task:"
+      name: Translation fao-eng
+      type: translation
+      args: fao-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba
+      args: fao-eng
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 30.1
+  - "task:"
+      name: Translation isl-eng
+      type: translation
+      args: isl-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba
+      args: isl-eng
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 53.3
+  - "task:"
+      name: Translation nno-eng
+      type: translation
+      args: nno-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba
+      args: nno-eng
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 56.1
+  - "task:"
+      name: Translation nob-eng
+      type: translation
+      args: nob-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba
+      args: nob-eng
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 60.2
+  - "task:"
+      name: Translation swe-eng
+      type: translation
+      args: swe-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba
+      args: swe-eng
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 66.4
+  - "task:"
+      name: Translation isl-eng
+      type: translation
+      args: isl-eng
+    dataset:
+      name: newstest2021.is-en
+      type: wmt-2021-news
+      args: isl-eng
+    metrics:
+  - "name: bleu"
+      type: bleu
+      value: 34.4
+---
 # opus-mt-tc-big-gmq-en
 
 Neural machine translation model for translating from North Germanic languages (gmq) to English (en).
@@ -49,7 +203,7 @@ This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus
 * model: transformer-big
 * data: opusTCv20210807+bt ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
 * tokenization: SentencePiece (spm32k,spm32k)
-* original model: [opusTCv20210807+bt_transformer-big_2022-03-09.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-eng/opusTCv20210807+bt_transformer-big_2022-03-09.zip)
+* original model: [opusTCv20210807+bt-big_2022-03-09.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-eng/opusTCv20210807+bt-big_2022-03-09.zip)
 * more information released models: [OPUS-MT gmq-eng README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/gmq-eng/README.md)
 
 ## Usage
@@ -59,18 +213,18 @@ A short example code:
 ```python
 from transformers import MarianMTModel, MarianTokenizer
 
-src_text = [
+src = [
     "Han var synligt nervøs.",
     "Inte ens Tom själv var övertygad."
 ]
 
-model_name = "pytorch-models/opus-mt-tc-big-gmq-en"
-tokenizer = MarianTokenizer.from_pretrained(model_name)
-model = MarianMTModel.from_pretrained(model_name)
-translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
+model = "pytorch-models/opus-mt-tc-big-gmq-en"
+tokenizer = MarianTokenizer.from(model)
+model = MarianMTModel.from(model)
+translated = model.generate(**tokenizer(src, return="pt", padding=True))
 
 for t in translated:
-    print( tokenizer.decode(t, skip_special_tokens=True) )
+    print( tokenizer.decode(t, skip_tokens=True) )
 
 # expected output:
 #     He was visibly nervous.
@@ -89,10 +243,10 @@ print(pipe("Han var synligt nervøs."))
 
 ## Benchmarks
 
-* test set translations: [opusTCv20210807+bt_transformer-big_2022-03-09.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-eng/opusTCv20210807+bt_transformer-big_2022-03-09.test.txt)
-* test set scores: [opusTCv20210807+bt_transformer-big_2022-03-09.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-eng/opusTCv20210807+bt_transformer-big_2022-03-09.eval.txt)
-* benchmark results: [benchmark_results.txt](benchmark_results.txt)
-* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
+* test set translations: [opusTCv20210807+bt-big_2022-03-09.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-eng/opusTCv20210807+bt-big_2022-03-09.test.txt)
+* test set scores: [opusTCv20210807+bt-big_2022-03-09.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-eng/opusTCv20210807+bt-big_2022-03-09.eval.txt)
+* benchmark results: [benchmark.txt](benchmark.txt)
+* benchmark output: [benchmark.zip](benchmark.zip)
 
 | langpair | testset | chr-F | BLEU  | #sent | #words |
 |----------|---------|-------|-------|-------|--------|

opus-mt-tc-big-gmq-en/meryem_muhur.txt

@@ -0,0 +1 @@
+Dogrulandi ve Meta-Veri Onarildi: Wed Apr 22 08:08:57 2026