By default trust remote code from HF Datasets (#9886) (#9887)

Signed-off-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: Nithin Rao <nithinrao.koluguri@gmail.com> Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
NVIDIA · Jul 25, 2024 · 363fb29 · 363fb29
1 parent 4e4b945
commit 363fb29
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/scripts/speech_recognition/convert_hf_dataset_to_nemo.py b/scripts/speech_recognition/convert_hf_dataset_to_nemo.py
@@ -362,6 +362,7 @@ def main(cfg: HFDatasetConversionConfig):
             cache_dir=None,
             streaming=cfg.streaming,
             token=cfg.use_auth_token,
+            trust_remote_code=True,
         )
 
     except Exception as e:

diff --git a/tutorials/asr/ASR_CTC_Language_Finetuning.ipynb b/tutorials/asr/ASR_CTC_Language_Finetuning.ipynb
@@ -225,7 +225,7 @@
       "cell_type": "code",
       "source": [
         "if not os.path.exists(\"convert_hf_dataset_to_nemo.py\"):\n",
-        "    !wget https://raw.githubusercontent.com/NVIDIA/NeMo/main/scripts/speech_recognition/convert_hf_dataset_to_nemo.py\n",
+        "    !wget https://raw.githubusercontent.com/NVIDIA/NeMo/$BRANCH/scripts/speech_recognition/convert_hf_dataset_to_nemo.py\n",
         ""
       ],
       "metadata": {
@@ -2217,4 +2217,4 @@
       ]
     }
   ]
-}
+}