fix: bug of None text on consecutive missing timestamps

MahmoudAshraf97 · Oct 15, 2023 · 570807e · 570807e
1 parent 71f6a74
commit 570807e
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/Whisper_Transcription_+_NeMo_Diarization.ipynb b/Whisper_Transcription_+_NeMo_Diarization.ipynb
@@ -409,7 +409,7 @@
         "    for i, ws in enumerate(word_timestamps[1:], start=1):\n",
         "        # if ws doesn't have a start and end\n",
         "        # use the previous end as start and next start as end\n",
-        "        if ws.get(\"start\") is None:\n",
+        "        if ws.get(\"start\") is None and ws.get(\"word\") is not None:\n",
         "            ws[\"start\"] = word_timestamps[i - 1][\"end\"]\n",
         "            ws[\"end\"] = _get_next_start_timestamp(word_timestamps, i)\n",
         "\n",

diff --git a/helpers.py b/helpers.py
@@ -343,7 +343,7 @@ def filter_missing_timestamps(word_timestamps):
     for i, ws in enumerate(word_timestamps[1:], start=1):
         # if ws doesn't have a start and end
         # use the previous end as start and next start as end
-        if ws.get("start") is None:
+        if ws.get("start") is None and ws.get("word") is not None:
             ws["start"] = word_timestamps[i - 1]["end"]
             ws["end"] = _get_next_start_timestamp(word_timestamps, i)