fix dataset token loading

Natooz · Mar 7, 2023 · 02793bb · 02793bb
1 parent fa8b85f
commit 02793bb
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/colab-notebooks/Full_Example_HuggingFace_GPT2_Transformer.ipynb b/colab-notebooks/Full_Example_HuggingFace_GPT2_Transformer.ipynb
@@ -110,10 +110,10 @@
     "                midi = MidiFile(file_path)\n",
     "                for _ in range(len(midi.instruments) - 1):\n",
     "                    del midi.instruments[1]  # removes all tracks except first one\n",
-    "                tokens = tokenizer.midi_to_tokens(midi)[0]\n",
+    "                tokens = tokenizer.midi_to_tokens(midi)[0].ids\n",
     "            else:\n",
     "                with open(file_path) as json_file:\n",
-    "                    tokens = json.load(json_file)['tokens'][0]  # first track\n",
+    "                    tokens = json.load(json_file)['ids'][0]  # first track\n",
     "            i = 0\n",
     "            while i < len(tokens):\n",
     "                if i >= len(tokens) - min_seq_len:\n",