lostecho/everyone-can-use-english
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

08-20-1635, chapter 4.2

Browse Source
This commit is contained in:
xiaolai
2024-08-20 16:54:07 +08:00
parent d16300fa0a
commit 83ecdf2ceb
3 changed files with 141 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

88
1000-hours/public/jupyter-notebooks/edge-tts-valcab-pronounciation.ipynb
View File

@@ -84,21 +84,10 @@
},
{
"cell_type": "code",
"execution_count": 84,
"execution_count": null,
"id": "4146f92e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['en-US-GuyNeural', 'en-US-AriaNeural']\n",
"important\n",
"../audios/important-us-male.mp3 created\n",
"../audios/important-us-female.mp3 created\n"
]
}
],
"outputs": [],
"source": [
"\n",
"voices = [\"en-US-GuyNeural\", \"en-US-AriaNeural\", \"en-GB-RyanNeural\", \"en-GB-LibbyNeural\"]\n",
@@ -112,7 +101,9 @@
" print(voices)\n",
"\n",
"words = \"\"\"\n",
"important\n",
"hello,\n",
"heat,\n",
"high,\n",
"\"\"\"\n",
"\n",
"for word in words.strip().split(','):\n",
@@ -126,7 +117,7 @@
},
{
"cell_type": "code",
"execution_count": 69,
"execution_count": 63,
"id": "2d46cde4",
"metadata": {},
"outputs": [],
@@ -146,18 +137,17 @@
" ) as response:\n",
" response.stream_to_file(path)\n",
" \n",
"sentence = \"It's a very important aspect\"\n",
"sentence = \"The explanation you gave was clear but I need a more detailed explanation.\"\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.rstrip(\",.?!\").translate(str.maketrans(' ,.?!', '-----')).strip().replace(\"--\", \"-\")\n",
"audio_filename_msedge = sentence.rstrip(\",.?!\").translate(str.maketrans(' ,.?!', '-----')).strip().replace(\"--\", \"-\")\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",
"# 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",
"for voice in [\"alloy\", \"nova\"]:\n",
" get_openai_tts_audio(sentence, f'../audios/{audio_filename_openai}-{voice}.mp3', performer=voice)\n"
" get_openai_tts_audio(sentence, f'../audios/{sentence.replace(\" \", \"-\")}-{voice}.mp3', performer=voice)\n"
]
},
{
@@ -271,62 +261,6 @@
"* voice = \"en-CA-ClaraNeural\" (Female)\n",
"* voice = \"en-CA-LiamNeural\" (Male)"
]
},
{
"cell_type": "code",
"execution_count": 79,
"id": "215d423d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<_io.BufferedRandom name='../audios/The-art-of-focus-in-our-whirlwind-existence-can-sometimes-feel-like-searching-for-a-needle-in-a-haystack-all-strong.mp3'>"
]
},
"execution_count": 79,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"text = \"\"\"\n",
"The art of focus in our whirlwind existence can sometimes feel like searching for a needle in a haystack\n",
"\"\"\"\n",
"\n",
"# 1 second silence with pydub\n",
"from pydub import AudioSegment\n",
"sentence = AudioSegment.silent(duration=1000)\n",
"\n",
"for word in text.strip().split(' '):\n",
" w = word.strip().lower()\n",
" if w == \"a\":\n",
" w = \"uh\"\n",
" if len(w) > 0:\n",
" filename = f'../audios/temp-{w.replace(\" \", \"-\")}-{regions[i]}-{genders[i]}.mp3'\n",
" get_openai_tts_audio(w, filename, performer=\"alloy\")\n",
" sentence += AudioSegment.from_file(filename) + AudioSegment.silent(duration=200)\n",
" # remove the temp file\n",
" os.remove(filename)\n",
"sentence += AudioSegment.silent(duration=1000)\n",
"# save the sentence as a single audio file\n",
"sentence.export(f'../audios/{text.strip().replace(\" \",\"-\")}-all-strong.mp3', format='mp3')\n"
]
},
{
"cell_type": "code",
"execution_count": 77,
"id": "5a718cf9",
"metadata": {},
"outputs": [],
"source": [
"text = \"\"\"\n",
"The art of focus in our whirlwind existence can sometimes feel like searching for a needle in a haystack\n",
"\"\"\"\n",
"filename = f'../audios/{text.strip().replace(\" \",\"-\")}-natural.mp3'\n",
"get_openai_tts_audio(text, filename, performer=\"alloy\")"
]
}
],
"metadata": {

127
1000-hours/public/jupyter-notebooks/phonetics.ipynb
View File

@@ -0,0 +1,127 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The history saving thread hit an unexpected error (DatabaseError('database disk image is malformed')).History will not be written to the database.\n"
]
}
],
"source": [
"import json\n",
"import vlc\n",
"import re\n",
"\n",
"# 假设你的 JSON 数据库是一个 JSON 文件，我们将从文件中加载数据\n",
"# 如果 JSON 数据在内存中或其他格式，你可能需要修改这部分代码\n",
"def load_json_database(file_path):\n",
" records = []\n",
" with open(file_path, 'r') as file:\n",
" for line in file:\n",
" try:\n",
" record = json.loads(line)\n",
" records.append(record)\n",
" except json.JSONDecodeError as e:\n",
" print(f\"Error parsing JSON: {e}\")\n",
" return records\n",
"\n",
"# The rest of the code remains the same...\n",
"\n",
"# 在 JSON 数据库中检索 word\n",
"def search_in_json_database(database, search_word, region):\n",
" for record in database:\n",
" # 检查 word 字段是否匹配\n",
" if record.get('word') == search_word:\n",
" # 找到匹配项后，获取美式发音信息\n",
" pos_items = record.get('pos_items', [])\n",
" for pos_item in pos_items:\n",
" pronunciations = pos_item.get('pronunciations', [])\n",
" for pronunciation in pronunciations:\n",
" if pronunciation.get('region') == region:\n",
" # 找到美式发音，返回相关信息\n",
" return {\n",
" 'pronunciation': pronunciation.get('pronunciation'),\n",
" 'audio': pronunciation.get('audio')\n",
" }\n",
" # 如果没有找到匹配的 word 字段，返回 'not exist'\n",
" return 'not exist'\n",
"\n",
"def search_pronunciation(database, pattern):\n",
" # Compile the regex pattern\n",
" regex = re.compile(pattern)\n",
" results = []\n",
" # Search in the database\n",
" for record in database:\n",
" for pos_item in record[\"pos_items\"]:\n",
" for pronunciation in pos_item[\"pronunciations\"]:\n",
" if regex.search(pronunciation[\"pronunciation\"]):\n",
" if pronunciation.get('region') == 'us':\n",
" results.append((record[\"word\"], pronunciation[\"pronunciation\"].replace(\".\", \"\"))) # record[\"_id\"][\"$oid\"],\n",
" # Return None if no match found\n",
" return results\n",
"\n",
"# 用于测试的 JSON 数据库文件路径\n",
"json_db_file_path = '/Users/joker/github/camdict/cam_dict.refined.json'\n",
"\n",
"json_database = load_json_database(json_db_file_path)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"*balls* <span class=\"pho alt\">bɑːlz</span><span class=\"speak-word-inline\" data-audio-us-male=\"/audios/ballss-us-male.mp3\" data-audio-us-female=\"/audios/ballss-us-female.mp3\"></span>\n",
"*cards* <span class=\"pho alt\">kɑrdz</span><span class=\"speak-word-inline\" data-audio-us-male=\"/audios/cardss-us-male.mp3\" data-audio-us-female=\"/audios/cardss-us-female.mp3\"></span>\n"
]
}
],
"source": [
"list = \"\"\"\n",
"balls,cards\n",
"\"\"\"\n",
"\n",
"for word in list.split(\",\"):\n",
" word = word.strip().lower()\n",
" result = search_in_json_database(json_database, word, 'us')\n",
" if result != 'not exist':\n",
" pho = result['pronunciation']\n",
" else:\n",
" pho = 'not exist'\n",
" line = f'*{word}* <span class=\"pho alt\">{pho}</span><span class=\"speak-word-inline\" data-audio-us-male=\"/audios/{word}s-us-male.mp3\" data-audio-us-female=\"/audios/{word}s-us-female.mp3\"></span>'\n",
" print(line)\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

6
1000-hours/sounds-of-american-english/4.2-words.md
View File

@@ -4,11 +4,11 @@
## 4.2.1. 重音、次重音、非重音、弱音
当一个词汇由一个以上的音节构成之时，其中的某个音节可能带有重音（*stress*），在音标中使用 <span class="pho">ˈ</span> 作为标记。
重点在于，英文的音节有**重音**、**次重音**、**非重音**的区别，这一点和亚洲语言明显不同。
如果一个单词只有一个音节，单独读出的时候，就当作是**重音**（*stress*）音节读出。而一个多音节词汇中**有且只有一个**重音音节，但，可能还有另外一些音节是**次重音**（*secondary stress*），在音标中使用 <span class="pho">ˌ</span> 作为标记。比如，*serendipity* <span class="pho alt">ˌserənˈdɪpət̬i</span><span class="speak-word-inline" data-audio-us-male="/audios/serendipity-us-male.mp3" data-audio-us-female="/audios/serendipity-us-female.mp3"></span>，有一个**重音**和一个**次重音**。而 *[Pneumonoultramicroscopicsilicovolcanoconiosis](https://en.wikipedia.org/wiki/Pneumonoultramicroscopicsilicovolcanoconiosis)*<span class="speak-word-inline" data-audio-us-female="/audios/En-us-pneumonoultramicroscopicsilicovolcanoconiosis.ogg.mp3"></span> 总计有 19 个音节，其中 7 个是次重音，唯一的重音是 <span class="pho">oʊ</span>……
**一个多音节词汇中最多只有一个重音音节**，但，可能还有另外一些音节是**次重音**（*secondary stress*），在音标中使用 <span class="pho">ˌ</span> 作为标记。比如，*serendipity* <span class="pho alt">ˌserənˈdɪpət̬i</span><span class="speak-word-inline" data-audio-us-male="/audios/serendipity-us-male.mp3" data-audio-us-female="/audios/serendipity-us-female.mp3"></span>，有一个**重音**和一个**次重音**。而 *[Pneumonoultramicroscopicsilicovolcanoconiosis](https://en.wikipedia.org/wiki/Pneumonoultramicroscopicsilicovolcanoconiosis)* 总计有 19 个音节，其中 7 个是次重音，唯一的重音是 <span class="pho">oʊ</span>……
另外一个重点在于，英文的音节有**重音**、**次重音**、**非重音**的区别，这一点也和亚洲语言明显不同。
形象地讲，5 个不分轻重的汉字（或者日文字、韩文字）排在一起大概是这样的：