translate french to fongbe

translations/urls.py

@@ -8,6 +8,6 @@ urlpatterns = [
     # path('UserTranslations/', TranslationListViewSet.as_view(), name="translations"),
     # path('TextToDeafSign/', TextToDeafSignViewSet.as_view(), name="text_to_deaf_sign"),
     # path('AudioToDeafSign/', AudioToDeafSignViewSet.as_view(), name="audio_to_deaf_sign"),
-    path('FongbeToFrText/', FongbeToFrancaisText.as_view(), name="fongbe_to_french_text"),
-    # path('AudioToText/', AudioToText.as_view(), name="audio_to_text")
+    path('translateTexte/', FongbeToFrancaisText.as_view(), name="fongbe_to_french_text"),
+    path('AudioToText/', AudioToText.as_view(), name="audio_to_text")
 ]

utils/data_prepared.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d5ff3aaa11b1d91c77f0278fe853719f6c26d4add6876e1ada409698ee2fab6e
-size 2529127

utils/datas/data_prepared_fr_fon/preprocess.log

@@ -0,0 +1,14 @@
+Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, cpu=False, tpu=False, bf16=False, memory_efficient_bf16=False, fp16=False, memory_efficient_fp16=False, fp16_no_flatten_grads=False, fp16_init_scale=128, fp16_scale_window=None, fp16_scale_tolerance=0.0, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='fr', target_lang='fon', trainpref='data_prepared/train', validpref='data_prepared/validation', testpref='data_prepared/test', align_suffix=None, destdir='data-bin/frfon.tokenized.fr-fon', thresholdtgt=0, thresholdsrc=0, tgtdict=None, srcdict=None, nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='mmap', joined_dictionary=False, only_source=False, padding_factor=8, workers=20, dict_only=False)
+[fr] Dictionary: 16904 types
+[fr] data_prepared/train.fr: 95161 sents, 562746 tokens, 0.0% replaced (by <unk>)
+[fr] Dictionary: 16904 types
+[fr] data_prepared/validation.fr: 20392 sents, 120545 tokens, 0.424% replaced (by <unk>)
+[fr] Dictionary: 16904 types
+[fr] data_prepared/test.fr: 20392 sents, 120961 tokens, 0.455% replaced (by <unk>)
+[fon] Dictionary: 17976 types
+[fon] data_prepared/train.fon: 95161 sents, 453730 tokens, 0.0% replaced (by <unk>)
+[fon] Dictionary: 17976 types
+[fon] data_prepared/validation.fon: 20392 sents, 97120 tokens, 0.901% replaced (by <unk>)
+[fon] Dictionary: 17976 types
+[fon] data_prepared/test.fon: 20392 sents, 96750 tokens, 0.943% replaced (by <unk>)
+Wrote preprocessed data to data-bin/frfon.tokenized.fr-fon

utils/utils_function.py

@@ -10,28 +10,14 @@ class Translator:
         # Charger le modèle pré-entraîné avec Fairseq
         inner = "fon_fr" if isFon else "fr_fon"
 
-        # if not os.path.exists('utils/data_prepared/'):
-        #     print("Not existed")
-
-        #     shutil.chmod('utils/', 0o777)
-
-        #     with zipfile.ZipFile('utils/data_prepared.zip', 'r') as zip_ref:
-        #         zip_ref.extractall('utils/')
-                
-        # else:
-        #     print("Existed")
-
         self.model = TransformerModel.from_pretrained(
-            './utils/checkpoints/fon_fr',
-            checkpoint_file='checkpoint_best.pt',
-            data_name_or_path='utils/data_prepared/',
-            source_lang='fon',
-            target_lang='fr'
+            f'./utils/checkpoints/{inner}',
+            checkpoint_file = 'checkpoint_best.pt',
+            data_name_or_path = f'utils/datas/data_prepared_{inner}/',
+            source_lang='fon' if isFon else 'fr',
+            target_lang='fr' if isFon else 'fon'
         )
 
-        print("#########################")
-        print(type(self.model))
-        print("#########################")
         # Définir le périphérique sur lequel exécuter le modèle (par défaut sur 'cuda' si disponible)
         self.model.to(device)