Add minds14 import

new_experiment/pipeline/import_datasets.py

@@ -32,4 +32,4 @@ def import_voxpopuli_dataset(dataset_lang: str, experiment_dataset_name: str):
         get_experiment_repository(experiment_dataset_name),
         get_minio_audio_record_repository(),
         experiment_dataset_name,
-    ), load_dataset('facebook/voxpopuli', dataset_lang))
+    ), load_dataset('facebook/voxpopuli', dataset_lang)['test'])

new_experiment/pipeline/import_minds14.py

+from new_experiment.pipeline.import_datasets import import_minds14_dataset
+
+if __name__ == '__main__':
+    import_minds14_dataset('nl-NL', 'nl_minds14')
+    import_minds14_dataset('fr-FR', 'fr_minds14')
+    import_minds14_dataset('de-DE', 'de_minds14')
+    import_minds14_dataset('it-IT', 'it_minds14')
+    import_minds14_dataset('pl-PL', 'pl_minds14')
+    import_minds14_dataset('es-ES', 'es_minds14')
+    import_minds14_dataset('en-US', 'en_minds14')

new_experiment/pipeline/import_voxpopuli.py

+from new_experiment.pipeline.import_datasets import import_voxpopuli_dataset
+
+if __name__ == '__main__':
+    import_voxpopuli_dataset('nl', 'nl_voxpopuli')
+    import_voxpopuli_dataset('fr', 'fr_voxpopuli')
+    import_voxpopuli_dataset('de', 'de_voxpopuli')
+    import_voxpopuli_dataset('it', 'it_voxpopuli')
+    import_voxpopuli_dataset('pl', 'pl_voxpopuli')
+    import_voxpopuli_dataset('es', 'es_voxpopuli')
+    import_voxpopuli_dataset('en', 'en_voxpopuli')