{"id":20849,"date":"2025-02-12T01:32:28","date_gmt":"2025-02-11T17:32:28","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=20849"},"modified":"2025-02-12T01:32:28","modified_gmt":"2025-02-11T17:32:28","slug":"zonos","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/en\/zonos\/","title":{"rendered":"Zonos\uff1a\u9ad8\u8d28\u91cf\u8bed\u97f3\u5408\u6210\u4e0e\u8bed\u97f3\u514b\u9686\u5de5\u5177"},"content":{"rendered":"<p>Zonos \u662f\u7531 Zyphra \u5f00\u53d1\u7684\u4e00\u6b3e\u5f00\u6e90\u8bed\u97f3\u5408\u6210\u4e0e\u8bed\u97f3\u514b\u9686\u5de5\u5177\u3002Zonos-v0.1 \u7248\u672c\u91c7\u7528\u4e86\u5148\u8fdb\u7684 <a href=\"https:\/\/www.kdjingpai.com\/pt\/transformer\/\">Transformer<\/a> \u548c\u6df7\u5408\u6a21\u578b\uff0c\u80fd\u591f\u751f\u6210\u9ad8\u8d28\u91cf\u7684\u8bed\u97f3\u8f93\u51fa\u3002\u8be5\u5de5\u5177\u652f\u6301\u591a\u79cd\u8bed\u8a00\uff0c\u5305\u62ec\u82f1\u8bed\u3001\u65e5\u8bed\u3001\u4e2d\u6587\u3001\u6cd5\u8bed\u548c\u5fb7\u8bed\uff0c\u5e76\u63d0\u4f9b\u7ec6\u81f4\u7684\u97f3\u9891\u8d28\u91cf\u548c\u60c5\u611f\u63a7\u5236\u3002Zonos \u7684\u8bed\u97f3\u514b\u9686\u529f\u80fd\u53ef\u4ee5\u5728\u63d0\u4f9b\u77ed\u77ed\u51e0\u79d2\u949f\u7684\u53c2\u8003\u97f3\u9891\u540e\uff0c\u751f\u6210\u9ad8\u5ea6\u81ea\u7136\u7684\u8bed\u97f3\u3002\u7528\u6237\u53ef\u4ee5\u901a\u8fc7 GitHub \u83b7\u53d6\u6a21\u578b\u6743\u91cd\u548c\u793a\u4f8b\u4ee3\u7801\uff0c\u5e76\u5728 Huggingface \u4e0a\u8fdb\u884c\u8bd5\u7528\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-20850\" title=\"Zonos\uff1a\u9ad8\u8d28\u91cf\u8bed\u97f3\u5408\u6210\u4e0e\u8bed\u97f3\u514b\u9686\u5de5\u5177-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/02\/a8bb2e25a365c69.jpg\" alt=\"Zonos\uff1a\u9ad8\u8d28\u91cf\u8bed\u97f3\u5408\u6210\u4e0e\u8bed\u97f3\u514b\u9686\u5de5\u5177-1\" width=\"1280\" height=\"720\" srcset=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/02\/a8bb2e25a365c69.jpg 1280w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/02\/a8bb2e25a365c69-768x432.jpg 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li><strong>\u96f6\u6837\u672c TTS \u8bed\u97f3\u514b\u9686<\/strong>\uff1a\u8f93\u5165\u6587\u672c\u548c10-30\u79d2\u7684\u8bf4\u8bdd\u8005\u6837\u672c\uff0c\u5373\u53ef\u751f\u6210\u9ad8\u8d28\u91cf\u7684\u8bed\u97f3\u8f93\u51fa\u3002<\/li>\n<li><strong>\u97f3\u9891\u524d\u7f00\u8f93\u5165<\/strong>\uff1a\u6dfb\u52a0\u6587\u672c\u548c\u97f3\u9891\u524d\u7f00\uff0c\u4ee5\u5b9e\u73b0\u66f4\u4e30\u5bcc\u7684\u8bf4\u8bdd\u8005\u5339\u914d\u3002<\/li>\n<li><strong>\u591a\u8bed\u8a00\u652f\u6301<\/strong>\uff1a\u652f\u6301\u82f1\u8bed\u3001\u65e5\u8bed\u3001\u4e2d\u6587\u3001\u6cd5\u8bed\u548c\u5fb7\u8bed\u3002<\/li>\n<li><strong>\u97f3\u9891\u8d28\u91cf\u548c\u60c5\u611f\u63a7\u5236<\/strong>\uff1a\u63d0\u4f9b\u5bf9\u751f\u6210\u97f3\u9891\u7684\u591a\u65b9\u9762\u7ec6\u81f4\u63a7\u5236\uff0c\u5305\u62ec\u8bf4\u8bdd\u901f\u5ea6\u3001\u97f3\u9ad8\u53d8\u5316\u3001\u97f3\u9891\u8d28\u91cf\u548c\u60c5\u611f\uff08\u5982\u5feb\u4e50\u3001\u6050\u60e7\u3001\u60b2\u4f24\u548c\u6124\u6012\uff09\u3002<\/li>\n<li><strong>\u5b9e\u65f6\u8bed\u97f3\u751f\u6210<\/strong>\uff1a\u652f\u6301\u5b9e\u65f6\u751f\u6210\u9ad8\u4fdd\u771f\u8bed\u97f3\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>\u514b\u9686\u9879\u76ee<\/strong>\uff1a\u5728\u7ec8\u7aef\u4e2d\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u4ee5\u514b\u9686 Zonos \u9879\u76ee\uff1a <code>bash<br \/>\ngit clone https:\/\/github.com\/Zyphra\/Zonos.git<br \/>\ncd Zonos<br \/>\n<\/code><\/li>\n<li><strong>\u5b89\u88c5\u4f9d\u8d56<\/strong>\uff1a\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\u6240\u9700\u7684 Python \u4f9d\u8d56\uff1a <code>bash<br \/>\npip install -r requirements.txt<br \/>\n<\/code><\/li>\n<li><strong>\u4e0b\u8f7d\u6a21\u578b\u6743\u91cd<\/strong>\uff1a\u4ece Huggingface \u4e0b\u8f7d\u6240\u9700\u7684\u6a21\u578b\u6743\u91cd\uff0c\u5e76\u5c06\u5176\u653e\u7f6e\u5728\u9879\u76ee\u76ee\u5f55\u4e2d\u3002<\/li>\n<\/ol>\n<h3>\u4f7f\u7528\u65b9\u6cd5<\/h3>\n<ol>\n<li><strong>\u52a0\u8f7d\u6a21\u578b<\/strong>\uff1a\u5728 Python \u73af\u5883\u4e2d\u52a0\u8f7d Zonos \u6a21\u578b\uff1a\n<pre><code>import torch\r\nimport torchaudio\r\nfrom zonos.model import Zonos\r\nfrom zonos.conditioning import make_cond_dict\r\nmodel = Zonos.from_pretrained(\"Zyphra\/Zonos-v0.1-transformer\", device=\"cuda\")\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u751f\u6210\u8bed\u97f3<\/strong>\uff1a\u63d0\u4f9b\u6587\u672c\u548c\u8bf4\u8bdd\u8005\u6837\u672c\uff0c\u751f\u6210\u8bed\u97f3\u8f93\u51fa\uff1a <code>python<br \/>\nwav, sampling_rate = torchaudio.load(\"assets\/exampleaudio.mp3\")<br \/>\nspeaker = model.make_speaker_embedding(wav, sampling_rate)<br \/>\ncond_dict = make_cond_dict(text=\"Hello, world!\", speaker=speaker, language=\"en-us\")<br \/>\nconditioning = model.prepare_conditioning(cond_dict)<br \/>\ncodes = model.generate(conditioning)<br \/>\nwavs = model.autoencoder.decode(codes).cpu()<br \/>\ntorchaudio.save(\"sample.wav\", wavs[0], model.autoencoder.sampling_rate)<br \/>\n<\/code><\/li>\n<li><strong>\u4f7f\u7528 Gradio \u63a5\u53e3<\/strong>\uff1a\u63a8\u8350\u4f7f\u7528 Gradio \u63a5\u53e3\u8fdb\u884c\u8bed\u97f3\u751f\u6210\uff1a <code>bash<br \/>\nuv run gradio_interface.py<br \/>\n# \u6216\u8005<br \/>\npython gradio_interface.py<br \/>\n<\/code> \u8fd9\u5c06\u751f\u6210\u4e00\u4e2a <code>sample.wav<\/code> \u6587\u4ef6\uff0c\u4fdd\u5b58\u5728\u9879\u76ee\u6839\u76ee\u5f55\u4e2d\u3002<\/li>\n<\/ol>\n<h3>\u8be6\u7ec6\u529f\u80fd\u64cd\u4f5c\u6d41\u7a0b<\/h3>\n<ol>\n<li><strong>\u96f6\u6837\u672c TTS \u8bed\u97f3\u514b\u9686<\/strong>\uff1a\n<ul>\n<li>\u8f93\u5165\u6240\u9700\u6587\u672c\u548c10-30\u79d2\u7684\u8bf4\u8bdd\u8005\u6837\u672c\uff0c\u6a21\u578b\u5c06\u751f\u6210\u9ad8\u8d28\u91cf\u7684\u8bed\u97f3\u8f93\u51fa\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u97f3\u9891\u524d\u7f00\u8f93\u5165<\/strong>\uff1a\n<ul>\n<li>\u6dfb\u52a0\u6587\u672c\u548c\u97f3\u9891\u524d\u7f00\uff0c\u4ee5\u5b9e\u73b0\u66f4\u4e30\u5bcc\u7684\u8bf4\u8bdd\u8005\u5339\u914d\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528\u4f4e\u8bed\u97f3\u9891\u524d\u7f00\u6765\u751f\u6210\u4f4e\u8bed\u6548\u679c\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u591a\u8bed\u8a00\u652f\u6301<\/strong>\uff1a\n<ul>\n<li>\u9009\u62e9\u6240\u9700\u8bed\u8a00\uff08\u5982\u82f1\u8bed\u3001\u65e5\u8bed\u3001\u4e2d\u6587\u3001\u6cd5\u8bed\u6216\u5fb7\u8bed\uff09\uff0c\u6a21\u578b\u5c06\u751f\u6210\u76f8\u5e94\u8bed\u8a00\u7684\u8bed\u97f3\u8f93\u51fa\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u97f3\u9891\u8d28\u91cf\u548c\u60c5\u611f\u63a7\u5236<\/strong>\uff1a\n<ul>\n<li>\u4f7f\u7528\u6a21\u578b\u7684\u6761\u4ef6\u8bbe\u7f6e\u529f\u80fd\uff0c\u7ec6\u81f4\u63a7\u5236\u751f\u6210\u97f3\u9891\u7684\u5404\u4e2a\u65b9\u9762\uff0c\u5305\u62ec\u8bf4\u8bdd\u901f\u5ea6\u3001\u97f3\u9ad8\u53d8\u5316\u3001\u97f3\u9891\u8d28\u91cf\u548c\u60c5\u611f\uff08\u5982\u5feb\u4e50\u3001\u6050\u60e7\u3001\u60b2\u4f24\u548c\u6124\u6012\uff09\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u5b9e\u65f6\u8bed\u97f3\u751f\u6210<\/strong>\uff1a\n<ul>\n<li>\u4f7f\u7528 Gradio \u63a5\u53e3\u6216\u5176\u4ed6\u5b9e\u65f6\u751f\u6210\u65b9\u6cd5\uff0c\u5feb\u901f\u751f\u6210\u9ad8\u4fdd\u771f\u8bed\u97f3\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>Zonos \u662f\u7531 Zyphra \u5f00\u53d1\u7684\u4e00\u6b3e\u5f00\u6e90\u8bed\u97f3\u5408\u6210\u4e0e\u8bed\u97f3\u514b\u9686\u5de5\u5177\u3002Zonos-v0.1 \u7248\u672c\u91c7\u7528\u4e86\u5148\u8fdb\u7684 Transformer \u548c\u6df7\u5408\u6a21\u578b\uff0c\u80fd\u591f\u751f\u6210\u9ad8\u8d28\u91cf\u7684\u8bed\u97f3\u8f93\u51fa\u3002\u8be5\u5de5\u5177\u652f\u6301\u591a\u79cd\u8bed\u8a00\uff0c\u5305\u62ec\u82f1\u8bed\u3001\u65e5\u8bed\u3001\u4e2d\u6587\u3001\u6cd5\u8bed\u548c\u5fb7\u8bed\uff0c\u5e76\u63d0\u4f9b\u7ec6\u81f4\u7684\u97f3&#8230;<\/p>\n","protected":false},"author":1,"featured_media":61819,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[230,237],"class_list":["post-20849","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","tag-aikaiyuanxiangmu","tag-aiyuyinkelong"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts\/20849","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/comments?post=20849"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts\/20849\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/media\/61819"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/media?parent=20849"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/categories?post=20849"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/tags?post=20849"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}