send editions to git

check_tokenizers.py

@@ -1,7 +1,7 @@
 from transformers import AutoTokenizer
 import json
 
-file = open('models_info.json', 'r')
+file = open('./data/models_info.json', 'r')
 models = json.load(file)
 
 # Strips the newline character

get_persian_nlp_models.py

@@ -1,16 +1,15 @@
 from huggingface_hub import HfApi, ModelFilter
 import json
 
-# Initialize the Hugging Face API
 api = HfApi()
 
-# Define the languages you're interested in
+# persian languages tags
 languages = ['pes', 'fas', 'fa']  # Language codes for Persian, Pashto, and Turkish
 nlp_tasks = ['text-classification', 'token-classification','table-question-answering','question-answering','zero-shot-classification','translation','summarization','feature-extraction','text-generation','text2text-generation','fill-mask','sentence-similarity']
-# Initialize a list to store the model information
+# list of model information
 models_info = []
 
-# Iterate over each language
+# Iterate languages
 for lang in languages:
     # Filter models by language
     models = api.list_models(filter=ModelFilter(language=lang))
@@ -30,8 +29,8 @@ for lang in languages:
         }
         models_info.append(model_info)
 
-# Save the collected data to a JSON file
-with open('models_info.json', 'w', encoding='utf-8') as f:
+# Save models_info
+with open('./data/models_info.json', 'w', encoding='utf-8') as f:
     json.dump(models_info, f, ensure_ascii=False, indent=4)
 
-print("Data collection complete. Saved to models_info.json")
+print("Finished!")