taco/microWakeWord-Trainer-Nvidia-Docker
1
0
Fork 0
mirror of https://github.com/TaterTotterson/microWakeWord-Trainer-Nvidia-Docker.git synced 2026-06-12 20:10:19 -06:00
Code Issues Packages Projects Releases Wiki Activity

Update advanced_training_notebook.ipynb

Browse Source
This commit is contained in:
MasterPhooey
2025-01-05 12:42:53 -06:00
committed by GitHub
parent 65adcdbc8f
commit 9cead7813a
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
advanced_training_notebook.ipynb
View File

@@ -205,8 +205,8 @@
" audioset_dataset = audioset_dataset.cast_column(\"audio\", Audio(sampling_rate=16000))\n", " audioset_dataset = audioset_dataset.cast_column(\"audio\", Audio(sampling_rate=16000))\n",
"\n", "\n",
" corrupted_files = []\n", " corrupted_files = []\n",
" print(\"Converting Audioset files to 16kHz WAV...\")\n",
"\n", "\n",
" print(\"Converting Audioset files to 16kHz WAV...\")\n",
" for row in tqdm(audioset_dataset, desc=\"Processing Audioset files\"):\n", " for row in tqdm(audioset_dataset, desc=\"Processing Audioset files\"):\n",
" try:\n", " try:\n",
" # Define output file name and path\n", " # Define output file name and path\n",
@@ -215,6 +215,8 @@
" \n", " \n",
" # Read and convert audio\n", " # Read and convert audio\n",
" data = row[\"audio\"][\"array\"]\n", " data = row[\"audio\"][\"array\"]\n",
" if data is None or len(data) == 0:\n",
" raise ValueError(f\"Empty audio data in file: {row['audio']['path']}\")\n",
" scipy.io.wavfile.write(output_path, 16000, (data * 32767).astype(np.int16))\n", " scipy.io.wavfile.write(output_path, 16000, (data * 32767).astype(np.int16))\n",
" \n", " \n",
" except Exception as e:\n", " except Exception as e:\n",