{"id":4062,"date":"2024-08-02T06:35:38","date_gmt":"2024-08-01T21:35:38","guid":{"rendered":"https:\/\/matoken.org\/blog\/?p=4062"},"modified":"2024-08-02T06:38:05","modified_gmt":"2024-08-01T21:38:05","slug":"downloading-the-model-data-of-whisper-cpp-fails-and-then-re-downloading-it","status":"publish","type":"post","link":"https:\/\/matoken.org\/blog\/2024\/08\/02\/downloading-the-model-data-of-whisper-cpp-fails-and-then-re-downloading-it\/","title":{"rendered":"whisper.cpp \u306e\u30e2\u30c7\u30eb\u30c7\u30fc\u30bf\u306e\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u306b\u5931\u6557\u3057\u305f\u3042\u3068\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u76f4\u3059"},"content":{"rendered":"<div class=\"paragraph\">\n<p>OpenAI \u306e Speach To Text \u306e Whisper \u3092 C\/C++ \u306b\u79fb\u690d\u3057\u305f\u3082\u306e\u304c\u3042\u308a\u307e\u3059\uff0e<br \/>\n\u65b0\u3057\u3044\u74b0\u5883\u3067\u4e45\u3057\u3076\u308a\u306b\u30bb\u30c3\u30c8\u30a2\u30c3\u30d7\u3057\u305f\u306e\u3067\u3059\u304c\uff0c\u30e2\u30c7\u30eb\u30c7\u30fc\u30bf\u306e\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u306b\u5931\u6557\u3057\u305f\u306e\u3067\u30e1\u30e2\u3057\u3066\u304a\u304d\u307e\u3059\uff0e<\/p>\n<\/div>\n<p><!--more--><\/p>\n<div class=\"ulist\">\n<ul>\n<li>\n<p><a href=\"https:\/\/github.com\/openai\/whisper\">openai\/whisper: Robust Speech Recognition via Large-Scale Weak Supervision<\/a><\/p>\n<\/li>\n<li>\n<p><a href=\"https:\/\/github.com\/ggerganov\/whisper.cpp\/\">ggerganov\/whisper.cpp: Port of OpenAI&#8217;s Whisper model in C\/C++<\/a><\/p>\n<\/li>\n<\/ul>\n<\/div>\n<div class=\"paragraph\">\n<p>whisper.cpp \u3067\u30e2\u30c7\u30eb\u30c7\u30fc\u30bf\u306e\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u306b\u3092\u884c\u3046\u306e\u306b make \u3084 .\/models\/download-ggml-model.sh \u304c\u4f7f\u3048\u307e\u3059\uff0e<\/p>\n<\/div>\n<div class=\"listingblock\">\n<div class=\"title\"><code>base<\/code> \u30e2\u30c7\u30eb\u306e\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u4f8b<\/div>\n<div class=\"content\">\n<pre>$ make base\n$ bash .\/models\/download-ggml-model.sh base<\/pre>\n<\/div>\n<\/div>\n<div class=\"paragraph\">\n<p>\u30e2\u30c7\u30eb\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u4e2d\u306b\u5931\u6557\u3057\u3066\u3057\u307e\u3046\u3068\u518d\u5ea6\u5b9f\u884c\u3057\u3066\u3082\u3082\u3046\u30d5\u30a1\u30a4\u30eb\u3042\u308b\u3088\u3068\u8a00\u308f\u308c\u3059\u3050\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u7d42\u4e86\u3057\u3066\u3057\u307e\u3044\u307e\u3059\uff0e<\/p>\n<\/div>\n<div class=\"listingblock\">\n<div class=\"content\">\n<pre>Model base already exists. Skipping download.<\/pre>\n<\/div>\n<\/div>\n<div class=\"paragraph\">\n<p>\u30e2\u30c7\u30eb\u30c7\u30fc\u30bf\u306f\u3069\u3046\u306a\u3063\u3066\u3044\u308b\u304b\u306a\u3068\u63a2\u3059\u3068\u6700\u8fd1\u306f <code>models<\/code> \u306e\u4e0b\u306b\u7f6e\u304f\u3088\u3046\u306a\u306e\u3067\u3053\u308c\u3092\u6d88\u3057\u3066\u518d\u5ea6\u5b9f\u884c\u3067\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u76f4\u305b\u308b\u3088\u3046\u3067\u3059\uff0c<\/p>\n<\/div>\n<div class=\"listingblock\">\n<div class=\"content\">\n<pre>$ rm models\/ggml-base.bin<\/pre>\n<\/div>\n<\/div>\n<div class=\"paragraph\">\n<p>\u3053\u3061\u3089\u306b sha1(!) hash \u304c\u3042\u308b\u306e\u3067\u3053\u308c\u3068\u5408\u81f4\u3057\u306a\u3044\u5834\u5408\u6d88\u3059\u3088\u3046\u306b\u3059\u308b\u3068\u826f\u3055\u305d\u3046\u3067\u3059\uff0e<\/p>\n<\/div>\n<div class=\"ulist\">\n<ul>\n<li>\n<p><a href=\"https:\/\/huggingface.co\/ggerganov\/whisper.cpp\">ggerganov\/whisper.cpp \u00b7 Hugging Face<\/a><\/p>\n<\/li>\n<\/ul>\n<\/div>\n<div class=\"listingblock\">\n<div class=\"content\">\n<pre>$ sha1sum models\/ggml-base.bin\n465707469ff3a37a2b9b8d8f89f2f99de7299dac  models\/ggml-base.bin<\/pre>\n<\/div>\n<\/div>\n<div class=\"paragraph\">\n<p>\u9014\u4e2d\u307e\u3067\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u304c\u9032\u3093\u3067\u3044\u308b\u5834\u5408\uff0cwget \u30b3\u30de\u30f3\u30c9\u306a\u3069\u3067\u7d9a\u304d\u304b\u3089\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3059\u308b\u3068\u8ee2\u9001\u6642\u9593\u304c\u5c11\u306a\u304f\u3066\u6e08\u307f\u307e\u3059\uff0e<br \/>\n\u30e2\u30c7\u30eb\u306e\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9URL \u306f\u4ee5\u4e0b\u306a\u3069\u304b\u3089\u78ba\u8a8d\u3067\u304d\u307e\u3059\uff0e<\/p>\n<\/div>\n<div class=\"ulist\">\n<ul>\n<li>\n<p><a href=\"https:\/\/huggingface.co\/ggerganov\/whisper.cpp\/tree\/main\">ggerganov\/whisper.cpp at main<\/a><\/p>\n<\/li>\n<\/ul>\n<\/div>\n<div class=\"admonitionblock note\">\n<table  class=\" table table-hover\" >\n<tr>\n<td class=\"icon\">\n<div class=\"title\">Note<\/div>\n<\/td>\n<td class=\"content\">\nlarge \u304c\u6b32\u3057\u3044\u5834\u5408\u3053\u306e\u4e2d\u306b\u898b\u5f53\u305f\u308a\u307e\u305b\u3093\u304c\uff0c <code>large-v3<\/code> \u304c\u305d\u308c\u306e\u3088\u3046\u3067\u3059\uff0e\n<\/td>\n<\/tr>\n<\/table>\n<\/div>\n<div class=\"listingblock\">\n<div class=\"title\">\u30d7\u30ed\u30b0\u30ec\u30b9\u306e <code>+<\/code> \u90e8\u5206\u306f\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u6e08\u3067\u30ec\u30b8\u30e5\u30fc\u30e0\u3057\u305f\u90e8\u5206\uff0c <code>=<\/code> \u304c\u4eca\u306e\u30bb\u30c3\u30b7\u30e7\u30f3\u3067\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u305f\u90e8\u5206<\/div>\n<div class=\"content\">\n<pre>$ wget -c \"https:\/\/huggingface.co\/ggerganov\/whisper.cpp\/resolve\/main\/ggml-base.bin?download=true\" \\\n-O models\/ggml-medium.bin\n\n--snip--\n\nmoodels\/ggml-medium.bin                      23%[+++++++++++++======&gt;                                ] 341.88M   632KB\/s<\/pre>\n<\/div>\n<\/div>\n<div class=\"paragraph\">\n<p>\u5b89\u5b9a\u3057\u305f\u74b0\u5883\u3060\u3068\u554f\u984c\u306a\u3044\u306e\u3067\u3057\u3087\u3046\u304c\u56de\u7dda\u3084\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u304c\u4e0d\u5b89\u5b9a\u3060\u3063\u305f\u308a(\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u3066\u3044\u308b\u306e\u3092\u5fd8\u308c\u3066\u30b5\u30b9\u30da\u30f3\u30c9\u3057\u3066\u3057\u307e\u3063\u305f\u308a)\u3059\u308b\u3068\u5d4c\u308b\u304b\u3082\u3057\u308c\u307e\u305b\u3093\uff0e<\/p>\n<\/div>\n<div class=\"listingblock\">\n<div class=\"title\">\u74b0\u5883<\/div>\n<div class=\"content\">\n<pre>$ git log -q -1\ncommit 6739eb83c3ca5cf40d24c6fe8442a761a1eb6248 (HEAD -&gt; master, origin\/master, origin\/HEAD)\nAuthor: Georgi Gerganov &lt;ggerganov@gmail.com&gt;\nDate:   Sat Jul 27 20:35:04 2024 +0300\n\n    whisper : handle empty mel (#2324)\n$ lsb_release -dr\nDescription:    Debian GNU\/Linux trixie\/sid\nRelease:        n\/a\n$ arch\nx86_64<\/pre>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>OpenAI \u306e Speach To Text \u306e Whisper \u3092 C\/C++ \u306b\u79fb\u690d\u3057\u305f\u3082\u306e\u304c\u3042\u308a\u307e\u3059\uff0e \u65b0\u3057\u3044\u74b0\u5883\u3067\u4e45\u3057\u3076\u308a\u306b\u30bb\u30c3\u30c8\u30a2\u30c3\u30d7\u3057\u305f\u306e\u3067\u3059\u304c\uff0c\u30e2\u30c7\u30eb\u30c7\u30fc\u30bf\u306e\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u306b\u5931\u6557\u3057\u305f\u306e\u3067\u30e1\u30e2\u3057\u3066\u304a\u304d\u307e\u3059\uff0e<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"webmentions_disabled_pings":false,"webmentions_disabled":false,"activitypub_content_warning":"","activitypub_content_visibility":"","activitypub_max_image_attachments":4,"activitypub_interaction_policy_quote":"anyone","activitypub_status":"federated","footnotes":""},"categories":[7,6,199],"tags":[256,824,825],"class_list":["post-4062","post","type-post","status-publish","format-standard","hentry","category-debian-linux","category-linux","category-sid","tag-wget","tag-whisper","tag-whisper-cpp"],"_links":{"self":[{"href":"https:\/\/matoken.org\/blog\/wp-json\/wp\/v2\/posts\/4062","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/matoken.org\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/matoken.org\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/matoken.org\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/matoken.org\/blog\/wp-json\/wp\/v2\/comments?post=4062"}],"version-history":[{"count":4,"href":"https:\/\/matoken.org\/blog\/wp-json\/wp\/v2\/posts\/4062\/revisions"}],"predecessor-version":[{"id":4066,"href":"https:\/\/matoken.org\/blog\/wp-json\/wp\/v2\/posts\/4062\/revisions\/4066"}],"wp:attachment":[{"href":"https:\/\/matoken.org\/blog\/wp-json\/wp\/v2\/media?parent=4062"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/matoken.org\/blog\/wp-json\/wp\/v2\/categories?post=4062"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/matoken.org\/blog\/wp-json\/wp\/v2\/tags?post=4062"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}