From ce8ff7fd354dbb7b8d3455045b05e00e95227f69 Mon Sep 17 00:00:00 2001
From: JustinSabatini <49084073+JustinSabatini@users.noreply.github.com>
Date: Fri, 14 Mar 2025 15:35:15 -0400
Subject: [PATCH] Update tts_realtime_demo.ipynb

Fix ESPnet2-TTS Colab Notebook: Update dependencies & ensure correct synthesis setup

This commit addresses three key issues in the ESPnet2-TTS realtime demonstration notebook:

- Fixed outdated SciPy import: Updated the installation step to use the 202412 version of ESPnet2, resolving an outdated kaiser import issue.

- Ensured nltk dataset availability: Added a condition in the "Model Setup" section to automatically download the required dataset before English synthesis.

- Resolved Japanese synthesis dependency issue: Introduced an additional condition to ensure pypopenjtalk is installed before running Japanese synthesis.

These fixes improve first-time usability by preventing common dependency errors in the notebook.
---
 ESPnet2/Demo/TTS/tts_realtime_demo.ipynb | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/ESPnet2/Demo/TTS/tts_realtime_demo.ipynb b/ESPnet2/Demo/TTS/tts_realtime_demo.ipynb
index 21bad3bb..6b0b6770 100644
--- a/ESPnet2/Demo/TTS/tts_realtime_demo.ipynb
+++ b/ESPnet2/Demo/TTS/tts_realtime_demo.ipynb
@@ -1,3 +1,4 @@
+
 {
   "nbformat": 4,
   "nbformat_minor": 0,
@@ -56,7 +57,7 @@
       },
       "source": [
         "# NOTE: pip shows imcompatible errors due to preinstalled libraries but you do not need to care\n",
-        "!pip install -q espnet==202308 pypinyin==0.44.0 parallel_wavegan==0.5.4 gdown==4.4.0 espnet_model_zoo\n"
+        "!pip install -q espnet==202412 pypinyin==0.44.0 parallel_wavegan==0.5.4 gdown==4.4.0 espnet_model_zoo\n"
       ],
       "execution_count": null,
       "outputs": []
@@ -192,7 +193,13 @@
         "    # Only for VITS\n",
         "    noise_scale=0.333,\n",
         "    noise_scale_dur=0.333,\n",
-        ")"
+        ")\n",
+        "\n",
+        "if lang == \"English\":\n",
+        "  import nltk\n",
+        "  nltk.download('averaged_perceptron_tagger_eng')\n",
+        "elif lang == \"Japanese\":\n",
+        "  !pip install -q pyopenjtalk"
       ],
       "execution_count": null,
       "outputs": []