release v0.4.0

- 更新 README 和用户手册，增加 Vosk 引擎的使用说明
- 修改构建配置，支持 Vosk 引擎的打包
- 更新版本号至 0.4.0，准备发布新功能

engine-test/trans.ipynb

@@ -0,0 +1,64 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "440d4a07",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "d:\\Projects\\auto-caption\\caption-engine\\subenv\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.\n"
+     ]
+    },
+    {
+     "ename": "ImportError",
+     "evalue": "\nMarianTokenizer requires the SentencePiece library but it was not found in your environment. Check out the instructions on the\ninstallation page of its repo: https://github.com/google/sentencepiece#installation and follow the ones\nthat match your environment. Please note that you may need to restart your runtime after installation.\n",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mImportError\u001b[39m                               Traceback (most recent call last)",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[1]\u001b[39m\u001b[32m, line 3\u001b[39m\n\u001b[32m      1\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mtransformers\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m MarianMTModel, MarianTokenizer\n\u001b[32m----> \u001b[39m\u001b[32m3\u001b[39m tokenizer = \u001b[43mMarianTokenizer\u001b[49m\u001b[43m.\u001b[49m\u001b[43mfrom_pretrained\u001b[49m(\u001b[33m\"\u001b[39m\u001b[33mHelsinki-NLP/opus-mt-en-zh\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m      4\u001b[39m model = MarianMTModel.from_pretrained(\u001b[33m\"\u001b[39m\u001b[33mHelsinki-NLP/opus-mt-en-zh\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m      6\u001b[39m tokenizer.save_pretrained(\u001b[33m\"\u001b[39m\u001b[33m./model_en_zh\u001b[39m\u001b[33m\"\u001b[39m)\n",
+      "\u001b[36mFile \u001b[39m\u001b[32md:\\Projects\\auto-caption\\caption-engine\\subenv\\Lib\\site-packages\\transformers\\utils\\import_utils.py:1994\u001b[39m, in \u001b[36mDummyObject.__getattribute__\u001b[39m\u001b[34m(cls, key)\u001b[39m\n\u001b[32m   1992\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m (key.startswith(\u001b[33m\"\u001b[39m\u001b[33m_\u001b[39m\u001b[33m\"\u001b[39m) \u001b[38;5;129;01mand\u001b[39;00m key != \u001b[33m\"\u001b[39m\u001b[33m_from_config\u001b[39m\u001b[33m\"\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m key == \u001b[33m\"\u001b[39m\u001b[33mis_dummy\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m key == \u001b[33m\"\u001b[39m\u001b[33mmro\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m key == \u001b[33m\"\u001b[39m\u001b[33mcall\u001b[39m\u001b[33m\"\u001b[39m:\n\u001b[32m   1993\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m().\u001b[34m__getattribute__\u001b[39m(key)\n\u001b[32m-> \u001b[39m\u001b[32m1994\u001b[39m \u001b[43mrequires_backends\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_backends\u001b[49m\u001b[43m)\u001b[49m\n",
+      "\u001b[36mFile \u001b[39m\u001b[32md:\\Projects\\auto-caption\\caption-engine\\subenv\\Lib\\site-packages\\transformers\\utils\\import_utils.py:1980\u001b[39m, in \u001b[36mrequires_backends\u001b[39m\u001b[34m(obj, backends)\u001b[39m\n\u001b[32m   1977\u001b[39m         failed.append(msg.format(name))\n\u001b[32m   1979\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m failed:\n\u001b[32m-> \u001b[39m\u001b[32m1980\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(\u001b[33m\"\u001b[39m\u001b[33m\"\u001b[39m.join(failed))\n",
+      "\u001b[31mImportError\u001b[39m: \nMarianTokenizer requires the SentencePiece library but it was not found in your environment. Check out the instructions on the\ninstallation page of its repo: https://github.com/google/sentencepiece#installation and follow the ones\nthat match your environment. Please note that you may need to restart your runtime after installation.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import MarianMTModel, MarianTokenizer\n",
+    "\n",
+    "tokenizer = MarianTokenizer.from_pretrained(\"Helsinki-NLP/opus-mt-en-zh\")\n",
+    "model = MarianMTModel.from_pretrained(\"Helsinki-NLP/opus-mt-en-zh\")\n",
+    "\n",
+    "tokenizer.save_pretrained(\"./model_en_zh\")\n",
+    "model.save_pretrained(\"./model_en_zh\")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "subenv",
+   "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": "3.12.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}