Fix Linux build (#341)

.github/workflows/ci.yml

@@ -21,6 +21,7 @@ jobs:
         include:
           - os: macos-latest
           - os: windows-latest
+          - os: ubuntu-20.04
     steps:
       - uses: actions/checkout@v3
         with:
@@ -63,7 +64,16 @@ jobs:
         run: poetry config experimental.new-installer false && poetry install
 
       - name: Test
-        run: poetry run make test
+        run: |
+          if [ "$RUNNER_OS" == "Linux" ]; then
+            sudo apt install libxkbcommon-x11-0 libxcb-icccm4 libxcb-image0 libxcb-keysyms1 libxcb-randr0 libxcb-render-util0 libxcb-xinerama0 libxcb-xfixes0 x11-utils
+            /sbin/start-stop-daemon --start --quiet --pidfile /tmp/custom_xvfb_99.pid --make-pidfile --background --exec /usr/bin/Xvfb -- :99 -screen 0 1920x1200x24 -ac +extension GLX
+            sudo apt update
+            sudo apt install -y libpulse-mainloop-glib0 libegl1-mesa-dev libgstreamer-plugins-base1.0-dev libgstreamer1.0-dev libportaudio2
+          fi
+          
+          poetry run make test
+        shell: bash
 
       - name: Upload coverage reports to Codecov with GitHub Action
         uses: codecov/codecov-action@v3
@@ -78,6 +88,7 @@ jobs:
         include:
           - os: macos-latest
           - os: windows-latest
+          - os: ubuntu-20.04
     steps:
       - uses: actions/checkout@v3
         with:
@@ -140,6 +151,10 @@ jobs:
 
           elif [ "$RUNNER_OS" == "Linux" ]; then
 
+            sudo apt install libxkbcommon-x11-0 libxcb-icccm4 libxcb-image0 libxcb-keysyms1 libxcb-randr0 libxcb-render-util0 libxcb-xinerama0 libxcb-xfixes0 x11-utils
+            /sbin/start-stop-daemon --start --quiet --pidfile /tmp/custom_xvfb_99.pid --make-pidfile --background --exec /usr/bin/Xvfb -- :99 -screen 0 1920x1200x24 -ac +extension GLX
+            sudo apt update
+            sudo apt install -y libpulse-mainloop-glib0 libegl1-mesa-dev libgstreamer-plugins-base1.0-dev libgstreamer1.0-dev libportaudio2 gettext
             poetry run make bundle_linux
 
           fi
@@ -161,6 +176,7 @@ jobs:
             dist/Buzz*-windows.tar.gz
             dist/Buzz*-windows.exe
             dist/Buzz*-mac.dmg
+            dist/Buzz*-unix.tar.gz
 
   release:
     runs-on: ${{ matrix.os }}
@@ -189,6 +205,7 @@ jobs:
         with:
           files: |
             Buzz*-windows.tar.gz
+            Buzz*-unix.tar.gz
             Buzz*-windows.exe
             Buzz*-mac.dmg
 

README.md

@@ -24,21 +24,31 @@ OpenAI's [Whisper](https://github.com/openai/whisper).
 ## Installation
 
 To install Buzz, download the [latest version](https://github.com/chidiwilliams/buzz/releases/latest) for your operating
-system. Buzz is available on **Mac** and **Windows**.
+system. Buzz is available on **Mac**, **Windows**, and **Linux**.
 
-### Mac (macOS 11.7 and above)
+### Mac (macOS 11.7 and later)
 
-Install via [brew](https://brew.sh/):
+- Install via [brew](https://brew.sh/):
 
-```shell
-brew install --cask buzz
-```
+    ```shell
+    brew install --cask buzz
+    ```
 
-Or, download and run the `Buzz-x.y.z.dmg` file.
+  Alternatively, download and run the `Buzz-x.y.z.dmg` file.
 
-### Windows
+### Windows (Windows 10 and later)
 
-Download and run the `Buzz-x.y.z.exe` file.
+- Download and run the `Buzz-x.y.z.exe` file.
+
+### Linux (Ubuntu 20.04 and later)
+
+- Install dependencies:
+
+    ```shell
+    sudo apt-get install libportaudio2
+    ```
+
+- Download and extract the `Buzz-x.y.z-unix.tar.gz` file
 
 ## How to use
 
@@ -97,10 +107,12 @@ and [Virtual Audio Cable](https://vac.muzychenko.net/en/)).
 
 To import a file:
 
-- Click Import on the File menu (or **Command + O** on Mac, **Ctrl + O** on Windows).
-- Choose an audio or video file. Supported formats: "mp3", "wav", "m4a", "ogg", "mp4", "webm", "ogm".
-- Select a task, language, quality, and export format.
+- Click Import Media File on the File menu (or the '+' icon on the toolbar, or **Command/Ctrl + O**).
+- Choose an audio or video file.
+- Select a task, language, and the model settings.
 - Click Run.
+- When the transcription status shows 'Completed', double-click on the row (or select the row and click the '⤢' icon) to
+  open the transcription.
 
 | Field              | Options             | Default | Description                                                                                                                                              |
 |--------------------|---------------------|---------|----------------------------------------------------------------------------------------------------------------------------------------------------------|

buzz/gui.py

@@ -341,11 +341,14 @@ class TranscriptionViewerWidget(QWidget):
     transcription_task: FileTranscriptionTask
 
     def __init__(
-            self, transcription_task: FileTranscriptionTask, parent: Optional['QWidget'] = None,
+            self, transcription_task: FileTranscriptionTask,
+            open_transcription_output=True,
+            parent: Optional['QWidget'] = None,
             flags: Qt.WindowType = Qt.WindowType.Widget,
     ) -> None:
         super().__init__(parent, flags)
         self.transcription_task = transcription_task
+        self.open_transcription_output = open_transcription_output
 
         self.setMinimumWidth(500)
         self.setMinimumHeight(500)
@@ -394,7 +397,7 @@ class TranscriptionViewerWidget(QWidget):
             return
 
         write_output(path=output_file_path, segments=self.transcription_task.segments,
-                     should_open=True, output_format=output_format)
+                     should_open=self.open_transcription_output, output_format=output_format)
 
 
 class AdvancedSettingsButton(QPushButton):

buzz/transcriber.py

@@ -483,8 +483,11 @@ def write_output(path: str, segments: List[Segment], should_open: bool, output_f
                     f'{to_timestamp(segment.start, ms_separator=",")} --> {to_timestamp(segment.end, ms_separator=",")}\n')
                 file.write(f'{segment.text}\n\n')
 
+    logging.debug('Written transcription output')
+
     if should_open:
         try:
+            logging.debug('Opening transcription output')
             os.startfile(path)
         except AttributeError:
             opener = "open" if platform.system() == "Darwin" else "xdg-open"

main.py

@@ -29,6 +29,9 @@ if platform.system() == 'Windows':
     os.add_dll_directory(app_dir)
 
 if __name__ == "__main__":
+    if platform.system() == 'Linux':
+        multiprocessing.set_start_method('spawn')
+
     # Fixes opening new window when app has been frozen on Windows:
     # https://stackoverflow.com/a/33979091
     multiprocessing.freeze_support()

tests/gui_test.py

@@ -1,4 +1,5 @@
 import logging
+import multiprocessing
 import os.path
 import pathlib
 import platform
@@ -27,6 +28,9 @@ from buzz.transcriber import (FileTranscriptionOptions, FileTranscriptionTask,
 from tests.mock_sounddevice import MockInputStream, mock_query_devices
 from .mock_qt import MockNetworkAccessManager, MockNetworkReply
 
+if platform.system() == 'Linux':
+    multiprocessing.set_start_method('spawn')
+
 
 @pytest.fixture(scope='module', autouse=True)
 def audio_setup():
@@ -369,7 +373,7 @@ class TestTranscriptionViewerWidget:
                 transcription_options=TranscriptionOptions(),
                 segments=[Segment(40, 299, 'Bien'),
                           Segment(299, 329, 'venue dans')],
-                model_path=''))
+                model_path=''), open_transcription_output=False)
         qtbot.add_widget(widget)
 
         assert widget.windowTitle() == 'whisper-french.mp3'
@@ -389,7 +393,7 @@ class TestTranscriptionViewerWidget:
                 transcription_options=TranscriptionOptions(),
                 segments=[Segment(40, 299, 'Bien'),
                           Segment(299, 329, 'venue dans')],
-                model_path=''))
+                model_path=''), open_transcription_output=False)
         qtbot.add_widget(widget)
 
         export_button = widget.findChild(QPushButton)