feat(gummy): 支持通过设置添加 API KEY

- 更新 main-gummy.py 以支持 API KEY 参数
- 修改 electron-builder.yml 以调整 Gummy 可执行文件路径

caption-engine/audio2text/gummy.py

@@ -4,6 +4,7 @@ from dashscope.audio.asr import (
     TranslationResult,
     TranslationRecognizerRealtime
 )
+import dashscope
 from datetime import datetime
 import json
 import sys
@@ -77,7 +78,9 @@ class GummyTranslator:
         source: 源语言代码字符串（zh, en, ja 等）
         target: 目标语言代码字符串（zh, en, ja 等）
     """
-    def __init__(self, rate, source, target):
+    def __init__(self, rate, source, target, api_key):
+        if api_key:
+            dashscope.api_key = api_key
         self.translator = TranslationRecognizerRealtime(
             model = "gummy-realtime-v1",
             format = "pcm",

caption-engine/main-gummy.py

@@ -14,14 +14,14 @@ from audioprcs import mergeChunkChannels
 from audio2text import InvalidParameter, GummyTranslator
 
 
-def convert_audio_to_text(s_lang, t_lang, audio_type, chunk_rate):
+def convert_audio_to_text(s_lang, t_lang, audio_type, chunk_rate, api_key):
     sys.stdout.reconfigure(line_buffering=True) # type: ignore
     stream = AudioStream(audio_type, chunk_rate)
 
     if t_lang == 'none':
-        gummy = GummyTranslator(stream.RATE, s_lang, None)
+        gummy = GummyTranslator(stream.RATE, s_lang, None, api_key)
     else:
-        gummy = GummyTranslator(stream.RATE, s_lang, t_lang)
+        gummy = GummyTranslator(stream.RATE, s_lang, t_lang, api_key)
 
     stream.openStream()
     gummy.start()
@@ -47,10 +47,12 @@ if __name__ == "__main__":
     parser.add_argument('-t', '--target_language', default='zh', help='Target language code')
     parser.add_argument('-a', '--audio_type', default=0, help='Audio stream source: 0 for output audio stream, 1 for input audio stream')
     parser.add_argument('-c', '--chunk_rate', default=20, help='The number of audio stream chunks collected per second.')
+    parser.add_argument('-k', '--api_key', default='', help='API KEY for Gummy model')
     args = parser.parse_args()
     convert_audio_to_text(
         args.source_language,
         args.target_language,
         int(args.audio_type),
-        int(args.chunk_rate)
+        int(args.chunk_rate),
+        args.api_key
     )

electron-builder.yml

@@ -10,8 +10,8 @@ files:
   - '!{.env,.env.*,.npmrc,pnpm-lock.yaml}'
   - '!{tsconfig.json,tsconfig.node.json,tsconfig.web.json}'
 extraResources:
-  from: ./caption-engine/dist/main-gummy.exe
+  from: ./caption-engine/dist/main-gummy
-  to: ./caption-engine/dist/main-gummy.exe
+  to: ./caption-engine/main-gummy
 asarUnpack:
   - resources/**
 win:

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "auto-caption",
-  "version": "0.2.1",
+  "version": "0.3.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "auto-caption",
-      "version": "0.2.1",
+      "version": "0.3.0",
       "hasInstallScript": true,
       "dependencies": {
         "@electron-toolkit/preload": "^3.0.1",

package.json

@@ -1,7 +1,7 @@
 {
   "name": "auto-caption",
   "productName": "Auto Caption",
-  "version": "0.2.1",
+  "version": "0.3.0",
   "description": "A cross-platform subtitle display software.",
   "main": "./out/main/index.js",
   "author": "himeditator",

src/main/i18n/lang/en.ts

@@ -1,5 +1,5 @@
 export default {
-  "gummy.env.missing": "DASHSCOPE_API_KEY environment variable not detected. To use the gummy engine, you need to obtain an API Key from Alibaba Cloud's Bailian platform and add it to your local environment variables.",
+  "gummy.key.missing": "API KEY is not set, and the DASHSCOPE_API_KEY environment variable is not detected. To use the gummy engine, you need to obtain an API KEY from the Alibaba Cloud Bailian platform and add it to the settings or configure it in the local environment variables.",
   "platform.unsupported": "Unsupported platform: ",
   "engine.start.error": "Caption engine failed to start: ",
   "engine.output.parse.error": "Unable to parse caption engine output as a JSON object: ",

src/main/i18n/lang/ja.ts

@@ -1,5 +1,5 @@
 export default {
-  "gummy.env.missing": "DASHSCOPE_API_KEY 環境変数が検出されませんでした。Gummy エンジンを使用するには、Alibaba Cloud の百煉プラットフォームから API Key を取得し、ローカル環境変数に追加する必要があります。",
+  "gummy.key.missing": "API KEY が設定されておらず、DASHSCOPE_API_KEY 環境変数も検出されていません。Gummy エンジンを使用するには、Alibaba Cloud Bailian プラットフォームから API KEY を取得し、設定に追加するか、ローカルの環境変数に設定する必要があります。",
   "platform.unsupported": "サポートされていないプラットフォーム: ",
   "engine.start.error": "字幕エンジンの起動に失敗しました: ",
   "engine.output.parse.error": "字幕エンジンの出力を JSON オブジェクトとして解析できませんでした: ",

src/main/i18n/lang/zh.ts

@@ -1,5 +1,5 @@
 export default {
-  "gummy.env.missing": "没有检测到 DASHSCOPE_API_KEY 环境变量，如果要使用 gummy 引擎，需要在阿里云百炼平台获取 API Key 并添加到本机环境变量",
+  "gummy.key.missing": "没有设置 API KEY，也没有检测到 DASHSCOPE_API_KEY 环境变量。如果要使用 gummy 引擎，需要在阿里云百炼平台获取 API KEY，并在添加到设置中或者配置到本机环境变量。",
   "platform.unsupported": "不支持的平台：",
   "engine.start.error": "字幕引擎启动失败：",
   "engine.output.parse.error": "字幕引擎输出内容无法解析为 JSON 对象：",

src/main/types/index.ts

@@ -9,6 +9,7 @@ export interface Controls {
   engine: 'gummy',
   audio: 0 | 1,
   translation: boolean,
+  API_KEY: string,
   customized: boolean,
   customizedApp: string,
   customizedCommand: string

src/main/utils/AllConfig.ts

@@ -26,6 +26,7 @@ const defaultControls: Controls = {
   engine: 'gummy',
   audio: 0,
   engineEnabled: false,
+  API_KEY: '',
   translation: true,
   customized: false,
   customizedApp: '',
@@ -82,7 +83,7 @@ class AllConfig {
     }
   }
 
-  public setStyles(args: Styles) {
+  public setStyles(args: Object) {
     for(let key in this.styles) {
       if(key in args) {
         this.styles[key] = args[key]
@@ -100,7 +101,7 @@ class AllConfig {
     console.log(`[INFO] Send Styles to #${window.id}:`, this.styles)
   }
 
-  public setControls(args: Controls) {
+  public setControls(args: Object) {
     const engineEnabled = this.controls.engineEnabled
     for(let key in this.controls){
       if(key in args) {

src/main/utils/CaptionEngine.ts

@@ -19,8 +19,8 @@ export class CaptionEngine {
     }
     else if (allConfig.controls.engine === 'gummy') {
       allConfig.controls.customized = false
-      if(!process.env.DASHSCOPE_API_KEY) {
+      if(!allConfig.controls.API_KEY && !process.env.DASHSCOPE_API_KEY) {
-        controlWindow.sendErrorMessage(i18n('gummy.env.missing'))
+        controlWindow.sendErrorMessage(i18n('gummy.key.missing'))
         return false
       }
       let gummyName = ''
@@ -42,8 +42,7 @@ export class CaptionEngine {
       }
       else {
         this.appPath = path.join(
-          process.resourcesPath,
+          process.resourcesPath, 'caption-engine', gummyName
-          'caption-engine', 'dist', gummyName
         )
       }
       this.command = []
@@ -53,6 +52,9 @@ export class CaptionEngine {
         allConfig.controls.targetLang : 'none'
       )
       this.command.push('-a', allConfig.controls.audio ? '1' : '0')
+      if(allConfig.controls.API_KEY) {
+        this.command.push('-k', allConfig.controls.API_KEY)
+      }
 
       console.log('[INFO] Engine Path:', this.appPath)
       console.log('[INFO] Engine Command:', this.command)
@@ -61,7 +63,7 @@ export class CaptionEngine {
   }
 
   public start() {
-    if (this.processStatus!== 'stopped') {
+    if (this.processStatus !== 'stopped') {
       return
     }
     if(!this.getApp()){ return }
@@ -122,7 +124,7 @@ export class CaptionEngine {
 
   public stop() {
     if(this.processStatus !== 'running') return
-    if (this.process) {
+    if (this.process.pid) {
       console.log('[INFO] Trying to stop process, PID:', this.process.pid)
       let cmd = `kill ${this.process.pid}`;
       if (process.platform === "win32") {
@@ -135,6 +137,17 @@ export class CaptionEngine {
         }
       })
     }
+    else {
+      this.process = undefined;
+      allConfig.controls.engineEnabled = false
+      if(controlWindow.window){
+        allConfig.sendControls(controlWindow.window)
+        controlWindow.window.webContents.send('control.engine.stopped')
+      }
+      this.processStatus = 'stopped'
+      console.log('[INFO] Process PID undefined, caption engine process stopped')
+      return
+    }
     this.processStatus = 'stopping'
     console.log('[INFO] Caption engine process stopping')
   }

src/renderer/src/components/EngineControl.vue

@@ -43,36 +43,51 @@
       <a-switch v-model:checked="currentTranslation" />
       <span style="display:inline-block;width:20px;"></span>
       <div style="display: inline-block;">
-        <span class="switch-label">{{ $t('engine.customEngine') }}</span>
+        <span class="switch-label">{{ $t('engine.showMore') }}</span>
-        <a-switch v-model:checked="currentCustomized" />
+        <a-switch v-model:checked="showMore" />
       </div>
     </div>
-    <div v-show="currentCustomized">
+    <a-card size="small" :title="$t('engine.custom.title')" v-show="showMore">
-      <a-card size="small" :title="$t('engine.custom.title')">
+      <div class="input-item">
-        <template #extra>
+        <span class="input-label">{{ $t('engine.apikey') }}</span>
-          <a-popover>
+        <a-input
-            <template #content>
+          class="input-area"
-              <p class="customize-note">{{ $t('engine.custom.note') }}</p>
+          type="password"
-            </template>
+          v-model:value="currentAPI_KEY"
-            <a><InfoCircleOutlined />{{ $t('engine.custom.attention') }}</a>
+        />
-          </a-popover>
+      </div>
-        </template>
+      <div class="input-item">
-        <div class="input-item">
+        <span style="margin-right:5px;">{{ $t('engine.customEngine') }}</span>
-          <span class="input-label">{{ $t('engine.custom.app') }}</span>
+        <a-switch v-model:checked="currentCustomized" />
-          <a-input
+      </div>
-            class="input-area"
+      <div v-show="currentCustomized">
-            v-model:value="currentCustomizedApp"
+        <a-card size="small" :title="$t('engine.custom.title')">
-          ></a-input>
+          <template #extra>
-        </div>
+            <a-popover>
-        <div class="input-item">
+              <template #content>
-          <span class="input-label">{{ $t('engine.custom.command') }}</span>
+                <p class="customize-note">{{ $t('engine.custom.note') }}</p>
-          <a-input
+              </template>
-            class="input-area"
+              <a><InfoCircleOutlined />{{ $t('engine.custom.attention') }}</a>
-            v-model:value="currentCustomizedCommand"
+            </a-popover>
-          ></a-input>
+          </template>
-        </div>
+          <div class="input-item">
-      </a-card>
+            <span class="input-label">{{ $t('engine.custom.app') }}</span>
-    </div>
+            <a-input
+              class="input-area"
+              v-model:value="currentCustomizedApp"
+            ></a-input>
+          </div>
+          <div class="input-item">
+            <span class="input-label">{{ $t('engine.custom.command') }}</span>
+            <a-input
+              class="input-area"
+              v-model:value="currentCustomizedCommand"
+            ></a-input>
+          </div>
+        </a-card>
+      </div>      
+    </a-card>
+
   </a-card>
   <div style="height: 20px;"></div>
 </template>
@@ -86,6 +101,7 @@ import { InfoCircleOutlined } from '@ant-design/icons-vue';
 import { useI18n } from 'vue-i18n'
 
 const { t } = useI18n()
+const showMore = ref(false)
 
 const engineControl = useEngineControlStore()
 const { platform, captionEngine, audioType, changeSignal } = storeToRefs(engineControl)
@@ -95,7 +111,7 @@ const currentTargetLang = ref('zh')
 const currentEngine = ref<'gummy'>('gummy')
 const currentAudio = ref<0 | 1>(0)
 const currentTranslation = ref<boolean>(false)
-
+const currentAPI_KEY = ref<string>('')
 const currentCustomized = ref<boolean>(false)
 const currentCustomizedApp = ref('')
 const currentCustomizedCommand = ref('')
@@ -115,7 +131,7 @@ function applyChange(){
   engineControl.engine = currentEngine.value
   engineControl.audio = currentAudio.value
   engineControl.translation = currentTranslation.value
-
+  engineControl.API_KEY = currentAPI_KEY.value
   engineControl.customized = currentCustomized.value
   engineControl.customizedApp = currentCustomizedApp.value
   engineControl.customizedCommand = currentCustomizedCommand.value
@@ -134,7 +150,7 @@ function cancelChange(){
   currentEngine.value = engineControl.engine
   currentAudio.value = engineControl.audio
   currentTranslation.value = engineControl.translation
-
+  currentAPI_KEY.value = engineControl.API_KEY
   currentCustomized.value = engineControl.customized
   currentCustomizedApp.value = engineControl.customizedApp
   currentCustomizedCommand.value = engineControl.customizedCommand

src/renderer/src/i18n/lang/en.ts

@@ -46,6 +46,8 @@ export default {
     "systemOutput": "System Audio Output (Speaker)",
     "systemInput": "System Audio Input (Microphone)",
     "enableTranslation": "Translation",
+    "showMore": "More Settings",
+    "apikey": "API KEY",
     "customEngine": "Custom Engine",
     custom: {
       "title": "Custom Caption Engine",

src/renderer/src/i18n/lang/ja.ts

@@ -46,6 +46,8 @@ export default {
     "systemOutput": "システムオーディオ出力（スピーカー）",
     "systemInput": "システムオーディオ入力（マイク）",
     "enableTranslation": "翻訳",
+    "showMore": "詳細設定",
+    "apikey": "API KEY",
     "customEngine": "カスタムエンジン",
     custom: {
       "title": "カスタムキャプションエンジン",

src/renderer/src/i18n/lang/zh.ts

@@ -46,6 +46,8 @@ export default {
     "systemOutput": "系统音频输出（扬声器）",
     "systemInput": "系统音频输入（麦克风）",
     "enableTranslation": "启用翻译",
+    "showMore": "更多设置",
+    "apikey": "API KEY",
     "customEngine": "自定义引擎",
     custom: {
       "title": "自定义字幕引擎",

src/renderer/src/stores/engineControl.ts

@@ -16,7 +16,7 @@ export const useEngineControlStore = defineStore('engineControl', () => {
 
   const captionEngine = ref(engines[useGeneralSettingStore().uiLanguage])
   const audioType = ref(audioTypes[useGeneralSettingStore().uiLanguage])
-
+  const API_KEY = ref<string>('')
   const engineEnabled = ref(false)
   const sourceLang = ref<string>('en')
   const targetLang = ref<string>('zh')
@@ -37,6 +37,7 @@ export const useEngineControlStore = defineStore('engineControl', () => {
       engine: engine.value,
       audio: audio.value,
       translation: translation.value,
+      API_KEY: API_KEY.value,
       customized: customized.value,
       customizedApp: customizedApp.value,
       customizedCommand: customizedCommand.value
@@ -51,6 +52,7 @@ export const useEngineControlStore = defineStore('engineControl', () => {
     audio.value = controls.audio
     engineEnabled.value = controls.engineEnabled
     translation.value = controls.translation
+    API_KEY.value = controls.API_KEY
     customized.value = controls.customized
     customizedApp.value = controls.customizedApp
     customizedCommand.value = controls.customizedCommand
@@ -108,6 +110,7 @@ export const useEngineControlStore = defineStore('engineControl', () => {
     engine,             // 字幕引擎
     audio,              // 选择音频
     translation,        // 是否启用翻译
+    API_KEY,            // API KEY
     customized,         // 是否使用自定义字幕引擎
     customizedApp,      // 自定义字幕引擎的应用程序
     customizedCommand,  // 自定义字幕引擎的命令

src/renderer/src/types/index.ts

@@ -9,6 +9,7 @@ export interface Controls {
   engine: 'gummy',
   audio: 0 | 1,
   translation: boolean,
+  API_KEY: string,
   customized: boolean,
   customizedApp: string,
   customizedCommand: string