Language is now optional and defaults to 'pl'

README.md

@@ -10,15 +10,17 @@ A service that automatically adds punctuation to raw word-stream (eg. from speec
 ## Config
 ```ini
 [deployment]
-device = cpu ; Device on which inference will be made (eg. cpu, cuda:0 etc)
-model_path = /model/punctuator ; Path where the model will be placed
-languagetool_path = /model/languagetool ; Path where languagetool server will be placed
+model_path_pl = /home/worker/model/punctuator_pl ; Path where the polish model is located
+model_path_en = /home/worker/model/punctuator_en ; Path where the polish model is located
+model_path_ru = /home/worker/model/punctuator_ru ; Path where the polish model is located
+languagetool_path = /home/worker/model/languagetool ; Path where languagetool server will be placed
 max_context_size = 256 ; Number of tokens that will be oonsidered in prediciton at once. Must be between in range 2*overlap+1 to 512
 overlap = 20 ; The number of tokens from the environment that will be taken at inference for a text fragment
+device = cpu ; Device on which inference will be made (eg. cpu, cuda:0 etc)
 ```
 
 ## LPMN
-Punctuator have one argument `language` with options: `pl` `ru` `en` :
+Punctuator have one optional argument `language` with options: `pl` `ru` `en` (defaults to pl):
 ```
 filedir(/users/michal.pogoda)|any2txt|punctuator({"language":"en"})
 ```

worker.py

@@ -63,12 +63,14 @@ class Worker(nlp_ws.NLPWorker):
     def process(
         self, input_path: str, task_options: dict, output_path: str
     ) -> None:
-        if task_options['language'] == 'en':
+        language = task_options.get("language", "pl")
+
+        if language == 'en':
             bpe = True
         else:
             bpe = False
         tool, model, tokenizer, mapping = self.get_setup_for_language(
-            task_options['language'])
+            language)
 
         with open(input_path, "r") as f:
             text = f.read()