dask force use

Signed-off-by: George Zelenfroind <gzelenfroind@nvidia.com>

Author: Jorjeous

sdp/processors/base_processor.py

@@ -82,7 +82,7 @@ def test(self):
         There are not tests by default.
         """
 
-class DaskParallelProcessor(BaseProcessor):
+class BaseParallelProcessor(BaseProcessor):
     """
     Processor class which allows operations on each entry to be parallelized using Dask.
 
@@ -251,7 +251,7 @@ def finalize(self, metrics: List[Any]):
 
 
 
-class BaseParallelProcessor(BaseProcessor):
+class LegacyParallelProcessor(BaseProcessor):
     """Processor class which allows operations on each utterance to be parallelized.
 
     Parallelization is done using ``tqdm.contrib.concurrent.process_map`` inside

sdp/processors/modify_manifest/common.py

@@ -24,7 +24,7 @@
     BaseParallelProcessor,
     BaseProcessor,
     DataEntry,
-    DaskParallelProcessor,
+    LegacyParallelProcessor,
 )
 from sdp.utils.common import load_manifest
 
@@ -99,9 +99,9 @@ def process_dataset_entry(self, data_entry: Dict):
         return [DataEntry(data=data_entry)]
 
 
-class AddConstantFields(DaskParallelProcessor):
+class AddConstantFields(BaseParallelProcessor):
     """
-    This processor adds constant fields to all manifest entries using DaskParallelProcessor.
+    This processor adds constant fields to all manifest entries using Dask BaseParallelProcessor.
     It is useful when you want to attach fixed information (e.g., a language label or metadata)
     to each entry for downstream tasks such as language identification model training.