From 665c47d24f485f6f09d999210662eebb1d591a2b Mon Sep 17 00:00:00 2001 From: himeditator Date: Sun, 13 Jul 2025 23:28:40 +0800 Subject: [PATCH] =?UTF-8?q?feat(linux):=20=E6=94=AF=E6=8C=81=20Linux=20?= =?UTF-8?q?=E7=B3=BB=E7=BB=9F=E9=9F=B3=E9=A2=91=E8=BE=93=E5=87=BA?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - 添加了对 Linux 系统音频输出的支持 - 更新了 README 和用户手册中的平台兼容性信息 - 修改了 AudioStream 类以支持 Linux 平台 --- .npmrc | 4 +- README.md | 33 ++++--- README_en.md | 31 +++++-- README_ja.md | 31 +++++-- caption-engine/main-vosk.spec | 6 +- ...quirements.txt => requirements_darwin.txt} | 1 - caption-engine/requirements_linux.txt | 5 ++ caption-engine/requirements_win.txt | 7 ++ caption-engine/sysaudio/linux.py | 87 ++++++++++++------- docs/user-manual/en.md | 24 +++++ docs/user-manual/ja.md | 24 +++++ docs/user-manual/zh.md | 25 +++++- engine-test/trans.ipynb | 64 -------------- src/main/utils/AllConfig.ts | 1 - src/main/utils/CaptionEngine.ts | 1 + src/renderer/src/components/EngineControl.vue | 1 - src/renderer/src/stores/engineControl.ts | 6 -- 17 files changed, 213 insertions(+), 138 deletions(-) rename caption-engine/{requirements.txt => requirements_darwin.txt} (64%) create mode 100644 caption-engine/requirements_linux.txt create mode 100644 caption-engine/requirements_win.txt delete mode 100644 engine-test/trans.ipynb diff --git a/.npmrc b/.npmrc index dcfa498..34862ff 100644 --- a/.npmrc +++ b/.npmrc @@ -1,2 +1,2 @@ -# electron_mirror=https://npmmirror.com/mirrors/electron/ -# electron_builder_binaries_mirror=https://npmmirror.com/mirrors/electron-builder-binaries/ +electron_mirror=https://npmmirror.com/mirrors/electron/ +electron_builder_binaries_mirror=https://npmmirror.com/mirrors/electron-builder-binaries/ diff --git a/README.md b/README.md index f1918e6..6a980a5 100644 --- a/README.md +++ b/README.md @@ -39,7 +39,15 @@ ## 📖 基本使用 -目前提供了 Windows 和 macOS 平台的可安装版本。 +软件已经适配了 Windows、macOS 和 Linux 平台。测试过的平台信息如下： + +| 操作系统版本 | 处理器架构 | 获取系统音频输入 | 获取系统音频输出 | +| ------------------ | ---------- | ---------------- | ---------------- | +| Windows 11 24H2 | x64 | ✅ | ✅ | +| macOS Sequoia 15.5 | arm64 | ✅需要额外配置 | ✅ | +| Ubuntu 24.04.2 | x64 | ✅需要额外配置 | ✅ | + +macOS 平台和 Linux 平台获取系统音频输出需要进行额外设置，详见[Auto Caption 用户手册](./docs/user-manual/zh.md)。 > 国际版的阿里云服务并没有提供 Gummy 模型，因此目前非中国用户无法使用 Gummy 字幕引擎。 @@ -54,7 +62,6 @@ ![](./assets/media/vosk_zh.png) - **如果你觉得上述字幕引擎不能满足你的需求，而且你会 Python，那么你可以考虑开发自己的字幕引擎。详细说明请参考[字幕引擎说明文档](./docs/engine-manual/zh.md)。** ## ✨ 特性 @@ -66,10 +73,6 @@ - 字幕记录展示与导出 - 生成音频输出或麦克风输入的字幕 -说明： -- Windows 和 macOS 平台支持生成音频输出和麦克风输入的字幕，但是 **macOS 平台获取系统音频输出需要进行设置，详见[Auto Caption 用户手册](./docs/user-manual/zh.md)** -- Linux 平台目前无法获取系统音频输出，仅支持生成麦克风输入的字幕 - ## ⚙️ 自带字幕引擎说明 目前软件自带 2 个字幕引擎，正在规划 1 个新的引擎。它们的详细信息如下。 @@ -137,12 +140,21 @@ subenv/Scripts/activate source subenv/bin/activate ``` -然后安装依赖（注意如果是 Linux 或 macOS 环境，需要注释掉 `requirements.txt` 中的 `PyAudioWPatch`，该模块仅适用于 Windows 环境）。 - -> 这一步可能会报错，一般是因为构建失败，需要根据报错信息安装对应的构建工具包。 +然后安装依赖（这一步可能会报错，一般是因为构建失败，需要根据报错信息安装对应的工具包）： ```bash -pip install -r requirements.txt +# Windows +pip install -r requirements_win.txt +# macOS +pip install -r requirements_darwin.txt +# Linux +pip install -r requirements_linux.txt +``` + +如果在 Linux 系统上安装 samplerate 模块报错，可以尝试使用以下命令单独安装： + +```bash +pip install samplerate --only-binary=:all: ``` 然后使用 `pyinstaller` 构建项目： @@ -168,6 +180,7 @@ vosk_path = str(Path('./subenv/lib/python3.x/site-packages/vosk').resolve()) ```bash npm run dev ``` + ### 构建项目 注意目前软件只在 Windows 和 macOS 平台上进行了构建和测试，无法保证软件在 Linux 平台下的正确性。 diff --git a/README_en.md b/README_en.md index b6ee71a..4d684c2 100644 --- a/README_en.md +++ b/README_en.md @@ -39,7 +39,15 @@ ## 📖 Basic Usage -Currently, installable versions are available for Windows and macOS platforms. +The software has been adapted for Windows, macOS, and Linux platforms. The tested platform information is as follows: + +| OS Version | Architecture | System Audio Input | System Audio Output | +| ------------------ | ------------ | ------------------ | ------------------- | +| Windows 11 24H2 | x64 | ✅ | ✅ | +| macOS Sequoia 15.5 | arm64 | ✅ Additional config required | ✅ | +| Ubuntu 24.04.2 | x64 | ✅ Additional config required | ✅ | + +Additional configuration is required to capture system audio output on macOS and Linux platforms. See [Auto Caption User Manual](./docs/user-manual/en.md) for details. > The international version of Alibaba Cloud services does not provide the Gummy model, so non-Chinese users currently cannot use the Gummy caption engine. @@ -65,10 +73,6 @@ To use the Vosk local caption engine, first download your required model from [V - Caption recording display and export - Generate captions for audio output or microphone input -Notes: -- Windows and macOS platforms support generating captions for both audio output and microphone input, but **macOS requires additional setup to capture system audio output. See [Auto Caption User Manual](./docs/user-manual/en.md) for details.** -- Linux platform currently cannot capture system audio output, only supports generating subtitles for microphone input. - ## ⚙️ Built-in Subtitle Engines Currently, the software comes with 2 subtitle engines, with 1 new engine planned. Details are as follows. @@ -136,12 +140,21 @@ subenv/Scripts/activate source subenv/bin/activate ``` -Then install dependencies (note: for Linux or macOS environments, you need to comment out `PyAudioWPatch` in `requirements.txt`, as this module is only for Windows environments). - -> This step may report errors, usually due to build failures. You need to install corresponding build tools based on the error messages. +Then install dependencies (this step may fail, usually due to build failures - you'll need to install the corresponding tool packages based on the error messages): ```bash -pip install -r requirements.txt +# Windows +pip install -r requirements_win.txt +# macOS +pip install -r requirements_darwin.txt +# Linux +pip install -r requirements_linux.txt +``` + +If you encounter errors when installing the `samplerate` module on Linux systems, you can try installing it separately with this command: + +```bash +pip install samplerate --only-binary=:all: ``` Then use `pyinstaller` to build the project: diff --git a/README_ja.md b/README_ja.md index ffe4c01..2a7fbc0 100644 --- a/README_ja.md +++ b/README_ja.md @@ -39,7 +39,15 @@ ## 📖 基本使い方 -現在、Windows と macOS プラットフォーム向けのインストール可能なバージョンを提供しています。 +このソフトウェアはWindows、macOS、Linuxプラットフォームに対応しています。テスト済みのプラットフォーム情報は以下の通りです： + +| OS バージョン | アーキテクチャ | システムオーディオ入力 | システムオーディオ出力 | +| ------------------ | ------------ | ------------------ | ------------------- | +| Windows 11 24H2 | x64 | ✅ | ✅ | +| macOS Sequoia 15.5 | arm64 | ✅ 追加設定が必要 | ✅ | +| Ubuntu 24.04.2 | x64 | ✅ 追加設定が必要 | ✅ | + +macOSおよびLinuxプラットフォームでシステムオーディオ出力を取得するには追加設定が必要です。詳細は[Auto Captionユーザーマニュアル](./docs/user-manual/ja.md)をご覧ください。 > 阿里雲の国際版サービスでは Gummy モデルを提供していないため、現在中国以外のユーザーは Gummy 字幕エンジンを使用できません。 @@ -65,10 +73,6 @@ Vosk ローカル字幕エンジンを使用するには、まず [Vosk Models]( - 字幕記録の表示とエクスポート - オーディオ出力またはマイク入力からの字幕生成 -注記： -- Windows と macOS プラットフォームはオーディオ出力とマイク入力の両方からの字幕生成をサポートしていますが、**macOS プラットフォームでシステムオーディオ出力を取得するには設定が必要です。詳細は[Auto Caption ユーザーマニュアル](./docs/user-manual/ja.md)をご覧ください。** -- Linux プラットフォームは現在システムオーディオ出力を取得できず、マイク入力からの字幕生成のみをサポートしています。 - ## ⚙️ 字幕エンジン説明 現在ソフトウェアには2つの字幕エンジンが組み込まれており、1つの新しいエンジンを計画中です。詳細は以下の通りです。 @@ -136,12 +140,21 @@ subenv/Scripts/activate source subenv/bin/activate ``` -その後、依存関係をインストールします（Linux または macOS 環境の場合、`requirements.txt` 内の `PyAudioWPatch` をコメントアウトする必要があります。このモジュールは Windows 環境専用です）。 - -> このステップでエラーが発生する場合があります。一般的にはビルド失敗が原因で、エラーメッセージに基づいて対応するビルドツールパッケージをインストールする必要があります。 +次に依存関係をインストールします（このステップは失敗する可能性があります、通常はビルド失敗が原因です - エラーメッセージに基づいて対応するツールパッケージをインストールする必要があります）： ```bash -pip install -r requirements.txt +# Windows +pip install -r requirements_win.txt +# macOS +pip install -r requirements_darwin.txt +# Linux +pip install -r requirements_linux.txt +``` + +Linuxシステムで`samplerate`モジュールのインストールに問題が発生した場合、以下のコマンドで個別にインストールを試すことができます： + +```bash +pip install samplerate --only-binary=:all: ``` その後、`pyinstaller` を使用してプロジェクトをビルドします： diff --git a/caption-engine/main-vosk.spec b/caption-engine/main-vosk.spec index aab7f83..4edbf8f 100644 --- a/caption-engine/main-vosk.spec +++ b/caption-engine/main-vosk.spec @@ -1,8 +1,12 @@ # -*- mode: python ; coding: utf-8 -*- from pathlib import Path +import sys -vosk_path = str(Path('./subenv/Lib/site-packages/vosk').resolve()) +if sys.platform == 'win32': + vosk_path = str(Path('./subenv/Lib/site-packages/vosk').resolve()) +else: + vosk_path = str(Path('./subenv/lib/python3.12/site-packages/vosk').resolve()) a = Analysis( ['main-vosk.py'], diff --git a/caption-engine/requirements.txt b/caption-engine/requirements_darwin.txt similarity index 64% rename from caption-engine/requirements.txt rename to caption-engine/requirements_darwin.txt index 0f168fb..0115a46 100644 --- a/caption-engine/requirements.txt +++ b/caption-engine/requirements_darwin.txt @@ -2,6 +2,5 @@ dashscope numpy samplerate PyAudio -PyAudioWPatch # Windows only vosk pyinstaller diff --git a/caption-engine/requirements_linux.txt b/caption-engine/requirements_linux.txt new file mode 100644 index 0000000..3574b4b --- /dev/null +++ b/caption-engine/requirements_linux.txt @@ -0,0 +1,5 @@ +dashscope +numpy +vosk +pyinstaller +samplerate # pip install samplerate --only-binary=:all: diff --git a/caption-engine/requirements_win.txt b/caption-engine/requirements_win.txt new file mode 100644 index 0000000..7ca77a4 --- /dev/null +++ b/caption-engine/requirements_win.txt @@ -0,0 +1,7 @@ +dashscope +numpy +samplerate +PyAudio +PyAudioWPatch +vosk +pyinstaller diff --git a/caption-engine/sysaudio/linux.py b/caption-engine/sysaudio/linux.py index 8e609a4..58be353 100644 --- a/caption-engine/sysaudio/linux.py +++ b/caption-engine/sysaudio/linux.py @@ -1,7 +1,34 @@ """获取 Linux 系统音频输入流""" -import pyaudio +import subprocess +def findMonitorSource(): + result = subprocess.run( + ["pactl", "list", "short", "sources"], + stdout=subprocess.PIPE, text=True + ) + lines = result.stdout.splitlines() + + for line in lines: + parts = line.split('\t') + if len(parts) >= 2 and ".monitor" in parts[1]: + return parts[1] + + raise RuntimeError("System output monitor device not found") + +def findInputSource(): + result = subprocess.run( + ["pactl", "list", "short", "sources"], + stdout=subprocess.PIPE, text=True + ) + lines = result.stdout.splitlines() + + for line in lines: + parts = line.split('\t') + name = parts[1] + if ".monitor" not in name: + return name + raise RuntimeError("Microphone input device not found") class AudioStream: """ @@ -13,26 +40,26 @@ class AudioStream: """ def __init__(self, audio_type=1, chunk_rate=20): self.audio_type = audio_type - self.mic = pyaudio.PyAudio() - self.device = self.mic.get_default_input_device_info() - self.stream = None - self.SAMP_WIDTH = pyaudio.get_sample_size(pyaudio.paInt16) - self.FORMAT = pyaudio.paInt16 - self.CHANNELS = self.device["maxInputChannels"] - self.RATE = int(self.device["defaultSampleRate"]) + + if self.audio_type == 0: + self.source = findMonitorSource() + else: + self.source = findInputSource() + + self.process = None + + self.SAMP_WIDTH = 2 + self.FORMAT = 16 + self.CHANNELS = 2 + self.RATE = 48000 self.CHUNK = self.RATE // chunk_rate - self.INDEX = self.device["index"] def printInfo(self): dev_info = f""" - 采样输入设备： - - 设备类型：{ "音频输入（Linux平台目前仅支持该项）" } - - 序号：{self.device['index']} - - 名称：{self.device['name']} - - 最大输入通道数：{self.device['maxInputChannels']} - - 默认低输入延迟：{self.device['defaultLowInputLatency']}s - - 默认高输入延迟：{self.device['defaultHighInputLatency']}s - - 默认采样率：{self.device['defaultSampleRate']}Hz + 音频捕获进程： + - 捕获类型：{"音频输出" if self.audio_type == 0 else "音频输入"} + - 设备源：{self.source} + - 捕获进程PID：{self.process.pid if self.process else "None"} 音频样本块大小：{self.CHUNK} 样本位宽：{self.SAMP_WIDTH} @@ -44,30 +71,24 @@ class AudioStream: def openStream(self): """ - 打开并返回系统音频输出流 + 启动音频捕获进程 """ - if self.stream: return self.stream - self.stream = self.mic.open( - format = self.FORMAT, - channels = int(self.CHANNELS), - rate = self.RATE, - input = True, - input_device_index = int(self.INDEX) + self.process = subprocess.Popen( + ["parec", "-d", self.source, "--format=s16le", "--rate=48000", "--channels=2"], + stdout=subprocess.PIPE ) - return self.stream def read_chunk(self): """ 读取音频数据 """ - if not self.stream: return None - return self.stream.read(self.CHUNK) + if self.process: + return self.process.stdout.read(self.CHUNK) + return None def closeStream(self): """ - 关闭系统音频输出流 + 关闭系统音频捕获进程 """ - if self.stream is None: return - self.stream.stop_stream() - self.stream.close() - self.stream = None + if self.process: + self.process.terminate() diff --git a/docs/user-manual/en.md b/docs/user-manual/en.md index 856a537..04954e6 100644 --- a/docs/user-manual/en.md +++ b/docs/user-manual/en.md @@ -61,6 +61,30 @@ Once BlackHole is confirmed installed, in the `Audio MIDI Setup` page, click the Now the caption engine can capture system audio output and generate captions. +## Getting System Audio Output on Linux + +Execute the following commands to install `pulseaudio` and `pavucontrol`: + +```bash +# For Debian or Ubuntu, etc. +sudo apt install pulseaudio pavucontrol +# For CentOS, etc. +sudo yum install pulseaudio pavucontrol +``` + +Then execute: + +```bash +pactl list short sources +``` + +If you see output similar to the following, the configuration was successful: + +```bash +220 alsa_output.pci-0000_02_02.0.3.analog-stereo.monitor PipeWire s16le 2ch 48000Hz SUSPENDED +221 alsa_input.pci-0000_02_02.0.3.analog-stereo PipeWire s16le 2ch 48000Hz SUSPENDED +``` + ## Software Usage ### Modifying Settings diff --git a/docs/user-manual/ja.md b/docs/user-manual/ja.md index 1e07915..9805922 100644 --- a/docs/user-manual/ja.md +++ b/docs/user-manual/ja.md @@ -64,6 +64,30 @@ BlackHoleのインストールが確認できたら、`オーディオ MIDI 設 これで字幕エンジンがシステムオーディオ出力をキャプチャし、字幕を生成できるようになります。 +## Linux でシステムオーディオ出力を取得する + +以下のコマンドを実行して `pulseaudio` と `pavucontrol` をインストールします: + +```bash +# Debian や Ubuntu など +sudo apt install pulseaudio pavucontrol +# CentOS など +sudo yum install pulseaudio pavucontrol +``` + +次に実行: + +```bash +pactl list short sources +``` + +以下のような出力があれば設定は成功です: + +```bash +220 alsa_output.pci-0000_02_02.0.3.analog-stereo.monitor PipeWire s16le 2ch 48000Hz SUSPENDED +221 alsa_input.pci-0000_02_02.0.3.analog-stereo PipeWire s16le 2ch 48000Hz SUSPENDED +``` + ## ソフトウェアの使い方 ### 設定の変更 diff --git a/docs/user-manual/zh.md b/docs/user-manual/zh.md index 74ce564..db53833 100644 --- a/docs/user-manual/zh.md +++ b/docs/user-manual/zh.md @@ -29,7 +29,6 @@ Auto Caption 是一个跨平台的字幕显示软件，能够实时获取系统 这部分阿里云提供了详细的教程，可参考： - [获取 API KEY](https://help.aliyun.com/zh/model-studio/get-api-key) - - [将 API Key 配置到环境变量](https://help.aliyun.com/zh/model-studio/configure-api-key-through-environment-variables) ## Vosk 引擎使用前准备 @@ -62,6 +61,30 @@ brew install blackhole-64ch 现在字幕引擎就能捕获系统的音频输出并生成字幕了。 +## Linux 获取系统音频输出 + +执行以下命令安装 `pulseaudio` 和 `pavucontrol`： + +```bash +# Debian or Ubuntu, etc. +sudo apt install pulseaudio pavucontrol +# CentOS, etc. +sudo yum install pulseaudio pavucontrol +``` + +然后执行： + +```bash +pactl list short sources +``` + +如果有以下类似的输出内容则配置成功： + +```bash +220 alsa_output.pci-0000_02_02.0.3.analog-stereo.monitor PipeWire s16le 2ch 48000Hz SUSPENDED +221 alsa_input.pci-0000_02_02.0.3.analog-stereo PipeWire s16le 2ch 48000Hz SUSPENDED +``` + ## 软件使用 ### 修改设置 diff --git a/engine-test/trans.ipynb b/engine-test/trans.ipynb deleted file mode 100644 index ff0b1dd..0000000 --- a/engine-test/trans.ipynb +++ /dev/null @@ -1,64 +0,0 @@ -{ - "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 -} diff --git a/src/main/utils/AllConfig.ts b/src/main/utils/AllConfig.ts index d3318ab..8bfd015 100644 --- a/src/main/utils/AllConfig.ts +++ b/src/main/utils/AllConfig.ts @@ -60,7 +60,6 @@ class AllConfig { if(config.uiTheme) this.uiTheme = config.uiTheme if(config.leftBarWidth) this.leftBarWidth = config.leftBarWidth if(config.styles) this.setStyles(config.styles) - if(process.platform !== 'win32' && process.platform !== 'darwin') config.controls.audio = 1 if(config.controls) this.setControls(config.controls) console.log('[INFO] Read Config from:', configPath) } diff --git a/src/main/utils/CaptionEngine.ts b/src/main/utils/CaptionEngine.ts index c254de9..a955146 100644 --- a/src/main/utils/CaptionEngine.ts +++ b/src/main/utils/CaptionEngine.ts @@ -118,6 +118,7 @@ export class CaptionEngine { }); this.process.stderr.on('data', (data) => { + if(this.processStatus === 'stopping') return controlWindow.sendErrorMessage(i18n('engine.error') + data) console.error(`[ERROR] Subprocess Error: ${data}`); }); diff --git a/src/renderer/src/components/EngineControl.vue b/src/renderer/src/components/EngineControl.vue index 7cd9907..7365d52 100644 --- a/src/renderer/src/components/EngineControl.vue +++ b/src/renderer/src/components/EngineControl.vue @@ -33,7 +33,6 @@
{{ $t('engine.audioType') }} { }); }) - watch(platform, (newValue) => { - if(newValue !== 'win32' && newValue !== 'darwin') { - audio.value = 1 - } - }) - return { platform, // 系统平台 captionEngine, // 字幕引擎列表