08-21-1355, chapter 4.3-group

1000-hours/public/jupyter-notebooks/edge-tts-valcab-pronounciation.ipynb

@@ -29,7 +29,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 2,
    "id": "71d35cd9",
    "metadata": {},
    "outputs": [
@@ -37,19 +37,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "['en-US-GuyNeural', 'en-US-AriaNeural']\n",
-      "hello\n",
-      "../audios/hello-us-male.mp3 created\n",
-      "../audios/hello-us-female.mp3 created\n",
-      "\n",
-      "heat\n",
-      "../audios/heat-us-male.mp3 created\n",
-      "../audios/heat-us-female.mp3 created\n",
-      "\n",
-      "high\n",
-      "../audios/high-us-male.mp3 created\n",
-      "../audios/high-us-female.mp3 created\n",
-      "\n"
+      "pygame 2.6.0 (SDL 2.28.4, Python 3.12.2)\n",
+      "Hello from the pygame community. https://www.pygame.org/contribute.html\n"
      ]
     }
    ],
@@ -84,10 +73,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "4146f92e",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['en-US-GuyNeural', 'en-US-AriaNeural']\n",
+      "apple\n",
+      "../audios/apple-us-male.mp3 exists, skipping...\n",
+      "../audios/apple-us-female.mp3 exists, skipping...\n",
+      "\n",
+      "impossible\n",
+      "../audios/impossible-us-male.mp3 exists, skipping...\n",
+      "../audios/impossible-us-female.mp3 exists, skipping...\n",
+      "\n",
+      "possible\n",
+      "../audios/possible-us-male.mp3 created\n",
+      "../audios/possible-us-female.mp3 created\n",
+      "\n",
+      "ichthyosaur\n",
+      "../audios/ichthyosaur-us-male.mp3 created\n",
+      "../audios/ichthyosaur-us-female.mp3 created\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "\n",
     "voices = [\"en-US-GuyNeural\", \"en-US-AriaNeural\", \"en-GB-RyanNeural\", \"en-GB-LibbyNeural\"]\n",
@@ -101,9 +114,11 @@
     "    print(voices)\n",
     "\n",
     "words = \"\"\"\n",
-    "hello,\n",
-    "heat,\n",
-    "high,\n",
+    "apple,\n",
+    "impossible,\n",
+    "possible,\n",
+    "ichthyosaur,\n",
+    "\n",
     "\"\"\"\n",
     "\n",
     "for word in words.strip().split(','):\n",
@@ -117,10 +132,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 63,
+   "execution_count": 15,
    "id": "2d46cde4",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "a-woman--without-her--man-is-nothing_openai.mp3\n"
+     ]
+    }
+   ],
    "source": [
     "def get_openai_tts_audio(text, path, performer='alloy'):\n",
     "        \n",
@@ -137,12 +160,14 @@
     "        ) as response:\n",
     "            response.stream_to_file(path)\n",
     "        \n",
-    "sentence = \"The explanation you gave was clear but I need a more detailed explanation.\"\n",
+    "sentence = \"A woman..., without her..., man is nothing.\"\n",
     "\n",
     "# remove all punctuation at the end of sentence,\n",
     "# replace all spaces and punctuations in the sentence with dash\n",
-    "audio_filename_openai = sentence.translate(str.maketrans(' ,.?!', '-----')).strip().replace(\"--\", \"-\") + '_openai.mp3'\n",
-    "audio_filename_msedge = sentence.translate(str.maketrans(' ,.?!', '-----')).strip().replace(\"--\", \"-\") + '_msedge.mp3'\n",
+    "audio_filename_openai = sentence.strip().translate(str.maketrans(',.?! ', '-----')).replace(\"--\", \"-\").lower().rstrip('-') + '_openai.mp3'\n",
+    "audio_filename_msedge = sentence.strip().translate(str.maketrans(',.?! ', '-----')).replace(\"--\", \"-\").lower().rstrip('-') + '_msedge.mp3'\n",
+    "\n",
+    "print(audio_filename_openai)\n",
     "# get_openai_tts_audio(sentence, audio_filename_openai, performer='alloy')\n",
     "# await generate_edge_tts_audio(sentence, audio_filename_msedge, voice=\"en-US-GuyNeural\", verbose=True, overwrite=True, play=True)\n",
     "\n",