{"id":18512,"date":"2025-01-08T10:42:38","date_gmt":"2025-01-08T02:42:38","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=18512"},"modified":"2025-07-20T06:08:19","modified_gmt":"2025-07-19T22:08:19","slug":"kokoro","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/de\/kokoro\/","title":{"rendered":"Kokoro\uff1a\u9ad8\u6548\u8bed\u97f3\u5408\u6210\u6a21\u578b\uff0c\u751f\u6210\u81ea\u7136\u6d41\u7545\u7684\u8bed\u97f3"},"content":{"rendered":"<p>Kokoro 82M \u662f\u7531 Hugging Face \u63d0\u4f9b\u7684\u4e00\u4e2a\u9ad8\u6548\u8bed\u97f3\u5408\u6210\u6a21\u578b\uff0c\u65e8\u5728\u901a\u8fc7\u8f83\u5c11\u7684\u53c2\u6570\u548c\u6570\u636e\u751f\u6210\u9ad8\u8d28\u91cf\u7684\u8bed\u97f3\u3002\u8be5\u6a21\u578b\u62e5\u6709 8200 \u4e07\u53c2\u6570\uff0c\u4f7f\u7528 Apache 2.0 \u8bb8\u53ef\u8bc1\u53d1\u5e03\uff0c\u652f\u6301\u591a\u79cd\u8bed\u97f3\u5305\uff08Voicepacks\uff09\uff0c\u53ef\u4ee5\u751f\u6210\u4e0d\u540c\u98ce\u683c\u548c\u8bed\u8a00\u7684\u8bed\u97f3\u3002Kokoro-82M \u5728 TTS\uff08Text-to-Speech\uff09\u9886\u57df\u8868\u73b0\u51fa\u8272\uff0c\u5c24\u5176\u5728 Elo \u6392\u540d\u4e2d\u8868\u73b0\u4f18\u5f02\uff0c\u80fd\u591f\u5728\u8f83\u5c11\u7684\u8ba1\u7b97\u8d44\u6e90\u4e0b\u5b9e\u73b0\u9ad8\u8d28\u91cf\u7684\u8bed\u97f3\u5408\u6210\u3002<\/p>\n<p>Kokoro \u5c01\u88c5\u7684API\uff1a<a href=\"https:\/\/www.kdjingpai.com\/kokoro-tts-api\/\">Kokoro TTS API\uff1a\u5feb\u901f\u6587\u672c\u8f6c\u8bed\u97f3\u7684Docker\u5316FastAPI\u5c01\u88c5\uff08Kokoro-82M\u6a21\u578b\uff09<\/a><\/p>\n<div id=\"attachment_18513\" style=\"width: 959px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-18513\" class=\"wp-image-18513 size-full\" title=\"Kokoro\uff1a\u9ad8\u6548\u8bed\u97f3\u5408\u6210\u6a21\u578b\uff0c\u751f\u6210\u81ea\u7136\u6d41\u7545\u7684\u8bed\u97f3-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/01\/1e5d4a2f95f16fd.png\" alt=\"Kokoro\uff1a\u9ad8\u6548\u8bed\u97f3\u5408\u6210\u6a21\u578b\uff0c\u751f\u6210\u81ea\u7136\u6d41\u7545\u7684\u8bed\u97f3-1\" width=\"949\" height=\"467\" srcset=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/01\/1e5d4a2f95f16fd.png 949w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/01\/1e5d4a2f95f16fd-300x148.png 300w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/01\/1e5d4a2f95f16fd-768x378.png 768w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/01\/1e5d4a2f95f16fd-18x9.png 18w\" sizes=\"auto, (max-width: 949px) 100vw, 949px\" \/><p id=\"caption-attachment-18513\" class=\"wp-caption-text\">\u4f53\u9a8c\u5730\u5740\uff1ahttps:\/\/huggingface.co\/spaces\/hexgrad\/Kokoro-TTS<\/p><\/div>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li><strong>\u8bed\u97f3\u5408\u6210<\/strong>\uff1a\u751f\u6210\u81ea\u7136\u6d41\u7545\u7684\u8bed\u97f3\u8f93\u51fa\u3002<\/li>\n<li><strong>\u591a\u8bed\u97f3\u5305\u652f\u6301<\/strong>\uff1a\u63d0\u4f9b\u591a\u79cd\u8bed\u97f3\u5305\uff0c\u7528\u6237\u53ef\u4ee5\u9009\u62e9\u4e0d\u540c\u7684\u58f0\u97f3\u98ce\u683c\u3002<\/li>\n<li><strong>\u9ad8\u6548\u6a21\u578b<\/strong>\uff1a\u4f7f\u7528\u8f83\u5c11\u7684\u53c2\u6570\u548c\u6570\u636e\u5b9e\u73b0\u9ad8\u8d28\u91cf\u7684\u8bed\u97f3\u5408\u6210\u3002<\/li>\n<li><strong>\u5f00\u6e90\u8bb8\u53ef<\/strong>\uff1a\u91c7\u7528 Apache 2.0 \u8bb8\u53ef\u8bc1\uff0c\u5141\u8bb8\u81ea\u7531\u4f7f\u7528\u548c\u4fee\u6539\u3002<\/li>\n<li><strong>\u793e\u533a\u652f\u6301<\/strong>\uff1a\u63d0\u4f9b Discord \u670d\u52a1\u5668\uff0c\u7528\u6237\u53ef\u4ee5\u5728\u793e\u533a\u4e2d\u8ba8\u8bba\u548c\u53cd\u9988\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5b89\u88c5\u6d41\u7a0b<\/h3>\n<ol>\n<li><strong>\u5b89\u88c5\u4f9d\u8d56<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   git lfs install\r\ngit clone https:\/\/huggingface.co\/hexgrad\/Kokoro-82M\r\ncd Kokoro-82M\r\napt-get -qq -y install espeak-ng &gt; \/dev\/null 2&gt;&amp;1\r\npip install -q phonemizer torch transformers scipy munch\r\n<\/code><\/pre>\n<ol start=\"2\">\n<li><strong>\u6784\u5efa\u6a21\u578b\u5e76\u52a0\u8f7d\u9ed8\u8ba4\u8bed\u97f3\u5305<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   from models import build_model\r\nimport torch\r\ndevice = 'cuda' if torch.cuda.is_available() else 'cpu'\r\nMODEL = build_model('kokoro-v0_19.pth', device)\r\nVOICE_NAME = 'af'  # \u9ed8\u8ba4\u8bed\u97f3\u5305\r\nVOICEPACK = torch.load(f'voices\/{VOICE_NAME}.pt', weights_only=True).to(device)\r\nprint(f'Loaded voice: {VOICE_NAME}')\r\n<\/code><\/pre>\n<ol start=\"3\">\n<li><strong>\u751f\u6210\u8bed\u97f3<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   from kokoro import generate\r\ntext = \"How could I know? It's an unanswerable question. Like asking an unborn child if they'll lead a good life. They haven't even been born.\"\r\naudio, out_ps = generate(MODEL, text, VOICEPACK, lang=VOICE_NAME[0])\r\nfrom IPython.display import display, Audio\r\ndisplay(Audio(data=audio, rate=24000, autoplay=True))\r\n<\/code><\/pre>\n<h3>\u4f7f\u7528\u8bf4\u660e<\/h3>\n<ol>\n<li><strong>\u9009\u62e9\u8bed\u97f3\u5305<\/strong>\uff1aKokoro-82M \u63d0\u4f9b\u591a\u79cd\u8bed\u97f3\u5305\uff0c\u7528\u6237\u53ef\u4ee5\u6839\u636e\u9700\u8981\u9009\u62e9\u4e0d\u540c\u7684\u58f0\u97f3\u98ce\u683c\u3002\u9ed8\u8ba4\u8bed\u97f3\u5305\u4e3a <code>af<\/code>\uff0c\u53ef\u4ee5\u5728 <code>voices<\/code> \u6587\u4ef6\u5939\u4e2d\u627e\u5230\u5176\u4ed6\u8bed\u97f3\u5305\u3002<\/li>\n<li><strong>\u751f\u6210\u8bed\u97f3<\/strong>\uff1a\u4f7f\u7528 <code>generate<\/code> \u51fd\u6570\u8f93\u5165\u6587\u672c\u5e76\u751f\u6210\u8bed\u97f3\u3002\u751f\u6210\u7684\u8bed\u97f3\u4e3a 24kHz\uff0c\u53ef\u4ee5\u901a\u8fc7 IPython \u663e\u793a\u64ad\u653e\u3002<\/li>\n<li><strong>\u8c03\u6574\u53c2\u6570<\/strong>\uff1a\u7528\u6237\u53ef\u4ee5\u6839\u636e\u9700\u8981\u8c03\u6574\u6a21\u578b\u53c2\u6570\u548c\u8bed\u97f3\u5305\uff0c\u4ee5\u83b7\u5f97\u6700\u4f73\u7684\u8bed\u97f3\u5408\u6210\u6548\u679c\u3002<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>Kokoro 82M \u662f\u7531 Hugging Face \u63d0\u4f9b\u7684\u4e00\u4e2a\u9ad8\u6548\u8bed\u97f3\u5408\u6210\u6a21\u578b\uff0c\u65e8\u5728\u901a\u8fc7\u8f83\u5c11\u7684\u53c2\u6570\u548c\u6570\u636e\u751f\u6210\u9ad8\u8d28\u91cf\u7684\u8bed\u97f3\u3002\u8be5\u6a21\u578b\u62e5\u6709 8200 \u4e07\u53c2\u6570\uff0c\u4f7f\u7528 Apache 2.0 \u8bb8\u53ef\u8bc1\u53d1\u5e03\uff0c\u652f\u6301\u591a\u79cd\u8bed\u97f3\u5305\uff08Voicepacks\uff09\uff0c\u53ef\u4ee5\u751f&#8230;<\/p>\n","protected":false},"author":1,"featured_media":31260,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[230,215],"class_list":["post-18512","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","tag-aikaiyuanxiangmu","tag-aiwenbenzhuanyuyin"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts\/18512","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/comments?post=18512"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts\/18512\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/media\/31260"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/media?parent=18512"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/categories?post=18512"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/tags?post=18512"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}