Fix issue with HF Model upload tutorial (NVIDIA#5359) (NVIDIA#5360)

* Add Gradio App to ASR Docs (NVIDIA#5270) Signed-off-by: smajumdar <[email protected]> Signed-off-by: smajumdar <[email protected]> (cherry picked from commit e4b6a38) * Fix issue with normalized config for dataset name Signed-off-by: smajumdar <[email protected]> Signed-off-by: smajumdar <[email protected]> Signed-off-by: smajumdar <[email protected]> Co-authored-by: Somshubra Majumdar <[email protected]> Signed-off-by: Vladimir Bataev <[email protected]>
artbataev · Nov 9, 2022 · 04d2912 · 04d2912
1 parent 9dc399e
commit 04d2912
Showing 1 changed file with 11 additions and 5 deletions.
diff --git a/tutorials/Publish_NeMo_Model_On_Hugging_Face_Hub.ipynb b/tutorials/Publish_NeMo_Model_On_Hugging_Face_Hub.ipynb
@@ -458,6 +458,7 @@
     {
       "cell_type": "code",
       "source": [
+        "# Replace all spaces with `-`\n",
         "DATASETS = [\n",
         "    \"librispeech_asr\",\n",
         "    \"mozilla-foundation/common_voice_7_0\",\n",
@@ -466,11 +467,11 @@
         "    \"Switchboard-1\",\n",
         "    \"WSJ-0\",\n",
         "    \"WSJ-1\",\n",
-        "    \"National Singapore Corpus Part 1\",\n",
-        "    \"National Singapore Corpus Part 6\",\n",
-        "    \"VoxPopuli (EN)\",\n",
-        "    \"Europarl-ASR (EN)\",\n",
-        "    \"Multilingual LibriSpeech (2000 hours)\",\n",
+        "    \"National-Singapore-Corpus-Part-1\",\n",
+        "    \"National-Singapore-Corpus-Part-6\",\n",
+        "    \"VoxPopuli-(EN)\",\n",
+        "    \"Europarl-ASR-(EN)\",\n",
+        "    \"Multilingual-LibriSpeech-(2000-hours)\",\n",
         "]"
       ],
       "metadata": {
@@ -520,9 +521,14 @@
         "config = OmegaConf.structured(config)\n",
         "\n",
         "with open_dict(config):\n",
+        "  # Update `model_index` to `model-index`\n",
         "  model_index = config.pop('model_index')\n",
         "  config['model-index'] = model_index\n",
         "\n",
+        "  # Replace all spaces with `-` in datasets\n",
+        "  normalized_datasets = [ds_name.replace(\" \", \"-\") for ds_name in config['datasets']]\n",
+        "  config['datasets'] = OmegaConf.create(normalized_datasets)\n",
+        "\n",
         "print(OmegaConf.to_yaml(config))"
       ],
       "metadata": {