GameSentenceMiner 2.14.5__tar.gz → 2.14.7__tar.gz

{gamesentenceminer-2.14.5 → gamesentenceminer-2.14.7}/GameSentenceMiner/obs.py

@@ -62,7 +62,7 @@ class OBSConnectionManager(threading.Thread):
         else:
             is_empty = extrema[0] == extrema[1]
         if is_empty:
-            logger.info("Image is totally empty (all pixels the same), sleeping.")
+            return
         else:
             root = tk.Tk()
             root.attributes('-topmost', True)

{gamesentenceminer-2.14.5 → gamesentenceminer-2.14.7}/GameSentenceMiner/ocr/owocr_helper.py

@@ -378,8 +378,16 @@ def text_callback(text, orig_text, time, img=None, came_from_ss=False, filtering
             previous_orig_text = orig_text_string
             previous_ocr1_result = previous_text
             if crop_coords and get_ocr_optimize_second_scan():
+                x1, y1, x2, y2 = crop_coords
+                x1 = max(0, min(x1, img.width))
+                y1 = max(0, min(y1, img.height))
+                x2 = max(x1, min(x2, img.width))
+                y2 = max(y1, min(y2, img.height))
                 previous_img_local.save(os.path.join(get_temporary_directory(), "pre_oneocrcrop.png"))
-                previous_img_local = previous_img_local.crop(crop_coords)
+                try:
+                    previous_img_local = previous_img_local.crop((x1, y1, x2, y2))
+                except ValueError:
+                    logger.warning("Error cropping image, using original image")
             second_ocr_queue.put((previous_text, stable_time, previous_img_local, filtering, pre_crop_image))
             # threading.Thread(target=do_second_ocr, args=(previous_text, stable_time, previous_img_local, filtering), daemon=True).start()
             previous_img = None
@@ -468,8 +476,6 @@ def add_ss_hotkey(ss_hotkey="ctrl+shift+g"):
         img = run.apply_ocr_config_to_image(img, ocr_config, is_secondary=True)
         do_second_ocr("", datetime.now(), img, TextFiltering(lang=get_ocr_language()), ignore_furigana_filter=True, ignore_previous_result=True)
         
-    if not manual:
-        keyboard.add_hotkey(get_ocr_manual_ocr_hotkey().lower(), ocr_secondary_rectangles)
     secret_ss_hotkey = "F14"
     filtering = TextFiltering(lang=get_ocr_language())
     cropper = ScreenCropper()
@@ -487,19 +493,29 @@ def add_ss_hotkey(ss_hotkey="ctrl+shift+g"):
     hotkey_reg = None
     try:
         hotkey_reg = keyboard.add_hotkey(ss_hotkey, capture)
+        if not manual:
+            secondary_hotkey_reg = keyboard.add_hotkey(get_ocr_manual_ocr_hotkey().lower(), ocr_secondary_rectangles)
         if "f13" in ss_hotkey.lower():
-            keyboard.add_hotkey(secret_ss_hotkey, capture_main_monitor)
+            secret_hotkey_reg = keyboard.add_hotkey(secret_ss_hotkey, capture_main_monitor)
         print(f"Press {ss_hotkey} to take a screenshot.")
     except Exception as e:
         if hotkey_reg:
             keyboard.remove_hotkey(hotkey_reg)
+        if secondary_hotkey_reg:
+            keyboard.remove_hotkey(secondary_hotkey_reg)
+        if secret_hotkey_reg:
+            keyboard.remove_hotkey(secret_hotkey_reg)
         logger.error(f"Error setting up screenshot hotkey with keyboard, Attempting Backup: {e}")
         logger.debug(e)
         pynput_hotkey = ss_hotkey.replace("ctrl", "<ctrl>").replace("shift", "<shift>").replace("alt", "<alt>")
+        secret_ss_hotkey = secret_hotkey_reg.replace("ctrl", "<ctrl>").replace("shift", "<shift>").replace("alt", "<alt>")
+        secondary_ss_hotkey = secondary_hotkey_reg.replace("ctrl", "<ctrl>").replace("shift", "<shift>").replace("alt", "<alt>")
         try:
             from pynput import keyboard as pynput_keyboard
             listener = pynput_keyboard.GlobalHotKeys({
-                pynput_hotkey: capture
+                pynput_hotkey: capture,
+                secondary_ss_hotkey: ocr_secondary_rectangles,
+                secret_ss_hotkey: capture_main_monitor
             })
             listener.start()
             print(f"Press {pynput_hotkey} to take a screenshot.")

{gamesentenceminer-2.14.5 → gamesentenceminer-2.14.7}/GameSentenceMiner/util/configuration.py

@@ -17,7 +17,6 @@ from dataclasses_json import dataclass_json
 
 from importlib import metadata
 
-import requests
 
 
 OFF = 'OFF'
@@ -361,6 +360,7 @@ def get_current_version():
 
 def get_latest_version():
     try:
+        import requests
         response = requests.get(f"https://pypi.org/pypi/{PACKAGE_NAME}/json")
         latest_version = response.json()["info"]["version"]
         return latest_version

{gamesentenceminer-2.14.5 → gamesentenceminer-2.14.7}/GameSentenceMiner/util/get_overlay_coords.py

@@ -134,10 +134,24 @@ class OverlayProcessor:
         composite_img = Image.new("RGBA", (monitor_width, monitor_height), (0, 0, 0, 0))
 
         for crop_coords in crop_coords_list:
-            cropped_image = full_screenshot.crop(crop_coords)
+            # Ensure crop coordinates are within image bounds
+            x1, y1, x2, y2 = crop_coords
+            x1 = max(0, min(x1, full_screenshot.width))
+            y1 = max(0, min(y1, full_screenshot.height))
+            x2 = max(x1, min(x2, full_screenshot.width))
+            y2 = max(y1, min(y2, full_screenshot.height))
+            
+            # Skip if the coordinates result in an invalid box
+            if x1 >= x2 or y1 >= y2:
+                continue
+            try:
+                cropped_image = full_screenshot.crop((x1, y1, x2, y2))
+            except ValueError:
+                logger.warning("Error cropping image, using original image")
+                return full_screenshot
             # Paste the cropped image onto the canvas at its original location
-            paste_x = math.floor(crop_coords[0])
-            paste_y = math.floor(crop_coords[1])
+            paste_x = math.floor(x1)
+            paste_y = math.floor(y1)
             composite_img.paste(cropped_image, (paste_x, paste_y))
         
         return composite_img

gamesentenceminer-2.14.7/GameSentenceMiner.egg-info/PKG-INFO

@@ -0,0 +1,169 @@
+Metadata-Version: 2.4
+Name: GameSentenceMiner
+Version: 2.14.7
+Summary: A tool for mining sentences from games. Update: Overlay?
+Author-email: Beangate <bpwhelan95@gmail.com>
+License: MIT License
+Project-URL: Homepage, https://github.com/bpwhelan/GameSentenceMiner
+Project-URL: Repository, https://github.com/bpwhelan/GameSentenceMiner
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests~=2.32.3
+Requires-Dist: watchdog~=5.0.2
+Requires-Dist: DateTime~=5.5
+Requires-Dist: pyperclip~=1.9.0
+Requires-Dist: soundfile~=0.12.1
+Requires-Dist: toml~=0.10.2
+Requires-Dist: psutil~=6.0.0
+Requires-Dist: rapidfuzz~=3.9.7
+Requires-Dist: plyer~=2.1.0
+Requires-Dist: keyboard~=0.13.5
+Requires-Dist: websockets~=15.0.1
+Requires-Dist: openai-whisper==20240930; sys_platform == "win32"
+Requires-Dist: openai-whisper; sys_platform != "win32"
+Requires-Dist: stable-ts-whisperless
+Requires-Dist: silero-vad~=5.1.2
+Requires-Dist: ttkbootstrap~=1.10.1
+Requires-Dist: dataclasses_json~=0.6.7
+Requires-Dist: win10toast; sys_platform == "win32"
+Requires-Dist: numpy==2.2.6
+Requires-Dist: pystray
+Requires-Dist: pywin32; sys_platform == "win32"
+Requires-Dist: pygetwindow; sys_platform == "win32"
+Requires-Dist: flask
+Requires-Dist: groq
+Requires-Dist: matplotlib
+Requires-Dist: sounddevice
+Requires-Dist: google-genai
+Requires-Dist: owocr
+Requires-Dist: oneocr
+Requires-Dist: openai
+Requires-Dist: scikit-image
+Requires-Dist: opencv-python
+Requires-Dist: betterproto==2.0.0b7
+Requires-Dist: obsws-python~=1.7.2
+Requires-Dist: numpy==2.2.6
+Requires-Dist: regex
+Dynamic: license-file
+
+# GSM - An Immersion toolkit for Games.
+
+### English | [日本語](../docs/ja/README.md) | [简体中文](../docs/zh/README.md).
+
+An application designed to assist with language learning through games.
+
+Short Demo (Watch this first): https://www.youtube.com/watch?v=FeFBL7py6HY
+
+Installation: https://youtu.be/h5ksXallc-o
+
+Discord: https://discord.gg/yP8Qse6bb8
+
+## Features
+
+### Anki Card Enhancement
+
+GSM significantly enhances your Anki cards with rich contextual information:
+
+* **Automated Audio Capture**: Automatically records the voice line associated with the text.
+
+  * **Automatic Trim**: Some simple math around the time that the text event came in, in combination with a "Voice Activation Detection" (VAD) library gives us neatly cut audio.
+  * **Manual Trim**: If Automatic voiceline trim is not perfect, it's possible to [open the audio in an external program](https://youtu.be/LKFQFy2Qm64) for trimming.
+
+* **Screenshot**: Captures a screenshot of the game at the moment the voice line is spoken.
+
+* **Multi-Line**: It's possible to capture multiple lines at once with sentence audio with GSM's very own Texthooker.
+
+* **AI Translation**: Integrates AI to provide quick translations of the captured sentence. Custom Prompts also supported. (Optional, Bring your own Key)
+
+
+#### Game Example (Has Audio)
+
+https://github.com/user-attachments/assets/df6bc38e-d74d-423e-b270-8a82eec2394c
+
+---
+
+#### VN Example (Has Audio)
+
+https://github.com/user-attachments/assets/ee670fda-1a8b-4dec-b9e6-072264155c6e
+
+### OCR
+
+GSM runs a fork of [OwOCR](https://github.com/AuroraWright/owocr/) to provide accurate text capture from games that do not have a hook. Here are some improvements GSM makes on stock OwOCR:
+
+* **Easier Setup**: With GSM's managed Python install, setup is only a matter of clicking a few buttons.
+
+* **Exclusion Zones**: Instead of choosing an area to OCR, you can choose an area to exclude from OCR. Useful if you have a static interface in your game and text appears randomly throughout.
+
+* **Two-Pass OCR**: To cut down on API calls and keep output clean, GSM features a "Two-Pass" OCR System. A Local OCR will be constantly running, and when the text on screen stabilizes, it will run a second, more accurate scan that gets sent to clipboard/WebSocket.
+
+* **Consistent Audio Timing**: With the two-pass system, we can still get accurate audio recorded and into Anki without the use of crazy offsets or hacks.
+
+* **More Language Support**: Stock OwOCR is hard-coded to Japanese, while in GSM you can use a variety of languages.
+
+
+https://github.com/user-attachments/assets/07240472-831a-40e6-be22-c64b880b0d66
+
+
+
+### Game Launcher Capabilities (WIP)
+
+This is probably the feature I care least about, but if you are lazy like me, you may find this helpful.
+
+* **Launch**:  GSM can launch your games directly, simplifying the setup process.
+
+* **Hook**:  Streamlines the process of hooking your games (Agent).
+
+This feature simplifies the process of launching games and (potentially) hooking them, making the entire workflow more efficient.
+
+<img width="2560" height="1392" alt="GameSentenceMiner_1zuov0R9xK" src="https://github.com/user-attachments/assets/205769bb-3dd2-493b-9383-2d6e2ca05c2d" />
+
+## Basic Requirements
+
+* **Anki card creation tool**: [Yomitan](https://github.com/yomidevs/yomitan), [JL](https://github.com/rampaa/JL), etc.
+
+* **A method of getting text from the game**: [Agent](https://github.com/0xDC00/agent), [Textractor](https://github.com/Artikash/Textractor), [LunaTranslator](https://github.com/HIllya51/LunaTranslator), GSM's OCR, etc.
+
+* **A game :)**
+
+## Documentation
+
+For help with installation, setup, and other information, please visit the project's [Wiki](https://github.com/bpwhelan/GameSentenceMiner/wiki).
+
+## FAQ
+
+### How Does It Work?
+
+This is a common question, and understanding this process will help clarify any issues you might encounter while using GSM.
+
+1.  The beginning of the voice line is marked by a text event. This usually comes from Textractor, Agent, or another texthooker. GSM can listen for a clipboard copy and/or a WebSocket server (configurable in GSM).
+
+2.  The end of the voice line is detected using a Voice Activity Detection (VAD) library running locally. ([Example](https://github.com/snakers4/silero-vad))
+
+In essence, GSM relies on accurately timed text events to capture the corresponding audio.
+
+GSM provides settings to accommodate less-than-ideal hooks. However, if you experience significant audio inconsistencies, they likely stem from a poorly timed hook, loud background music, or other external factors, rather than GSM itself. The core audio trimming logic has been stable and effective for many users across various games.
+
+## Contact
+
+If you encounter issues, please ask for help in my [Discord](https://discord.gg/yP8Qse6bb8) or create an issue here.
+
+## Acknowledgements
+
+* [OwOCR](https://github.com/AuroraWright/owocr) for their outstanding OCR implementation, which I've integrated into GSM.
+
+* [chaiNNer](https://github.com/chaiNNer-org/chaiNNer) for the idea of installing Python within an Electron app.
+
+* [OBS](https://obsproject.com/) and [FFMPEG](https://ffmpeg.org/), without which GSM would not be possible.
+
+* [Renji's Texthooker](https://github.com/Renji-XD/texthooker-ui)
+
+* https://github.com/Saplling/transparent-texthooker-overlay
+
+## Donations
+
+If you've found this or any of my other projects helpful, please consider supporting my work through [GitHub Sponsors](https://github.com/sponsors/bpwhelan), or [Ko-fi](https://ko-fi.com/beangate).
+

{gamesentenceminer-2.14.5 → gamesentenceminer-2.14.7}/GameSentenceMiner.egg-info/SOURCES.txt

@@ -1,4 +1,5 @@
 LICENSE
+README.md
 pyproject.toml
 GameSentenceMiner/__init__.py
 GameSentenceMiner/anki.py

gamesentenceminer-2.14.7/PKG-INFO

@@ -0,0 +1,169 @@
+Metadata-Version: 2.4
+Name: GameSentenceMiner
+Version: 2.14.7
+Summary: A tool for mining sentences from games. Update: Overlay?
+Author-email: Beangate <bpwhelan95@gmail.com>
+License: MIT License
+Project-URL: Homepage, https://github.com/bpwhelan/GameSentenceMiner
+Project-URL: Repository, https://github.com/bpwhelan/GameSentenceMiner
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests~=2.32.3
+Requires-Dist: watchdog~=5.0.2
+Requires-Dist: DateTime~=5.5
+Requires-Dist: pyperclip~=1.9.0
+Requires-Dist: soundfile~=0.12.1
+Requires-Dist: toml~=0.10.2
+Requires-Dist: psutil~=6.0.0
+Requires-Dist: rapidfuzz~=3.9.7
+Requires-Dist: plyer~=2.1.0
+Requires-Dist: keyboard~=0.13.5
+Requires-Dist: websockets~=15.0.1
+Requires-Dist: openai-whisper==20240930; sys_platform == "win32"
+Requires-Dist: openai-whisper; sys_platform != "win32"
+Requires-Dist: stable-ts-whisperless
+Requires-Dist: silero-vad~=5.1.2
+Requires-Dist: ttkbootstrap~=1.10.1
+Requires-Dist: dataclasses_json~=0.6.7
+Requires-Dist: win10toast; sys_platform == "win32"
+Requires-Dist: numpy==2.2.6
+Requires-Dist: pystray
+Requires-Dist: pywin32; sys_platform == "win32"
+Requires-Dist: pygetwindow; sys_platform == "win32"
+Requires-Dist: flask
+Requires-Dist: groq
+Requires-Dist: matplotlib
+Requires-Dist: sounddevice
+Requires-Dist: google-genai
+Requires-Dist: owocr
+Requires-Dist: oneocr
+Requires-Dist: openai
+Requires-Dist: scikit-image
+Requires-Dist: opencv-python
+Requires-Dist: betterproto==2.0.0b7
+Requires-Dist: obsws-python~=1.7.2
+Requires-Dist: numpy==2.2.6
+Requires-Dist: regex
+Dynamic: license-file
+
+# GSM - An Immersion toolkit for Games.
+
+### English | [日本語](../docs/ja/README.md) | [简体中文](../docs/zh/README.md).
+
+An application designed to assist with language learning through games.
+
+Short Demo (Watch this first): https://www.youtube.com/watch?v=FeFBL7py6HY
+
+Installation: https://youtu.be/h5ksXallc-o
+
+Discord: https://discord.gg/yP8Qse6bb8
+
+## Features
+
+### Anki Card Enhancement
+
+GSM significantly enhances your Anki cards with rich contextual information:
+
+* **Automated Audio Capture**: Automatically records the voice line associated with the text.
+
+  * **Automatic Trim**: Some simple math around the time that the text event came in, in combination with a "Voice Activation Detection" (VAD) library gives us neatly cut audio.
+  * **Manual Trim**: If Automatic voiceline trim is not perfect, it's possible to [open the audio in an external program](https://youtu.be/LKFQFy2Qm64) for trimming.
+
+* **Screenshot**: Captures a screenshot of the game at the moment the voice line is spoken.
+
+* **Multi-Line**: It's possible to capture multiple lines at once with sentence audio with GSM's very own Texthooker.
+
+* **AI Translation**: Integrates AI to provide quick translations of the captured sentence. Custom Prompts also supported. (Optional, Bring your own Key)
+
+
+#### Game Example (Has Audio)
+
+https://github.com/user-attachments/assets/df6bc38e-d74d-423e-b270-8a82eec2394c
+
+---
+
+#### VN Example (Has Audio)
+
+https://github.com/user-attachments/assets/ee670fda-1a8b-4dec-b9e6-072264155c6e
+
+### OCR
+
+GSM runs a fork of [OwOCR](https://github.com/AuroraWright/owocr/) to provide accurate text capture from games that do not have a hook. Here are some improvements GSM makes on stock OwOCR:
+
+* **Easier Setup**: With GSM's managed Python install, setup is only a matter of clicking a few buttons.
+
+* **Exclusion Zones**: Instead of choosing an area to OCR, you can choose an area to exclude from OCR. Useful if you have a static interface in your game and text appears randomly throughout.
+
+* **Two-Pass OCR**: To cut down on API calls and keep output clean, GSM features a "Two-Pass" OCR System. A Local OCR will be constantly running, and when the text on screen stabilizes, it will run a second, more accurate scan that gets sent to clipboard/WebSocket.
+
+* **Consistent Audio Timing**: With the two-pass system, we can still get accurate audio recorded and into Anki without the use of crazy offsets or hacks.
+
+* **More Language Support**: Stock OwOCR is hard-coded to Japanese, while in GSM you can use a variety of languages.
+
+
+https://github.com/user-attachments/assets/07240472-831a-40e6-be22-c64b880b0d66
+
+
+
+### Game Launcher Capabilities (WIP)
+
+This is probably the feature I care least about, but if you are lazy like me, you may find this helpful.
+
+* **Launch**:  GSM can launch your games directly, simplifying the setup process.
+
+* **Hook**:  Streamlines the process of hooking your games (Agent).
+
+This feature simplifies the process of launching games and (potentially) hooking them, making the entire workflow more efficient.
+
+<img width="2560" height="1392" alt="GameSentenceMiner_1zuov0R9xK" src="https://github.com/user-attachments/assets/205769bb-3dd2-493b-9383-2d6e2ca05c2d" />
+
+## Basic Requirements
+
+* **Anki card creation tool**: [Yomitan](https://github.com/yomidevs/yomitan), [JL](https://github.com/rampaa/JL), etc.
+
+* **A method of getting text from the game**: [Agent](https://github.com/0xDC00/agent), [Textractor](https://github.com/Artikash/Textractor), [LunaTranslator](https://github.com/HIllya51/LunaTranslator), GSM's OCR, etc.
+
+* **A game :)**
+
+## Documentation
+
+For help with installation, setup, and other information, please visit the project's [Wiki](https://github.com/bpwhelan/GameSentenceMiner/wiki).
+
+## FAQ
+
+### How Does It Work?
+
+This is a common question, and understanding this process will help clarify any issues you might encounter while using GSM.
+
+1.  The beginning of the voice line is marked by a text event. This usually comes from Textractor, Agent, or another texthooker. GSM can listen for a clipboard copy and/or a WebSocket server (configurable in GSM).
+
+2.  The end of the voice line is detected using a Voice Activity Detection (VAD) library running locally. ([Example](https://github.com/snakers4/silero-vad))
+
+In essence, GSM relies on accurately timed text events to capture the corresponding audio.
+
+GSM provides settings to accommodate less-than-ideal hooks. However, if you experience significant audio inconsistencies, they likely stem from a poorly timed hook, loud background music, or other external factors, rather than GSM itself. The core audio trimming logic has been stable and effective for many users across various games.
+
+## Contact
+
+If you encounter issues, please ask for help in my [Discord](https://discord.gg/yP8Qse6bb8) or create an issue here.
+
+## Acknowledgements
+
+* [OwOCR](https://github.com/AuroraWright/owocr) for their outstanding OCR implementation, which I've integrated into GSM.
+
+* [chaiNNer](https://github.com/chaiNNer-org/chaiNNer) for the idea of installing Python within an Electron app.
+
+* [OBS](https://obsproject.com/) and [FFMPEG](https://ffmpeg.org/), without which GSM would not be possible.
+
+* [Renji's Texthooker](https://github.com/Renji-XD/texthooker-ui)
+
+* https://github.com/Saplling/transparent-texthooker-overlay
+
+## Donations
+
+If you've found this or any of my other projects helpful, please consider supporting my work through [GitHub Sponsors](https://github.com/sponsors/bpwhelan), or [Ko-fi](https://ko-fi.com/beangate).
+

gamesentenceminer-2.14.7/README.md

@@ -0,0 +1,117 @@
+# GSM - An Immersion toolkit for Games.
+
+### English | [日本語](../docs/ja/README.md) | [简体中文](../docs/zh/README.md).
+
+An application designed to assist with language learning through games.
+
+Short Demo (Watch this first): https://www.youtube.com/watch?v=FeFBL7py6HY
+
+Installation: https://youtu.be/h5ksXallc-o
+
+Discord: https://discord.gg/yP8Qse6bb8
+
+## Features
+
+### Anki Card Enhancement
+
+GSM significantly enhances your Anki cards with rich contextual information:
+
+* **Automated Audio Capture**: Automatically records the voice line associated with the text.
+
+  * **Automatic Trim**: Some simple math around the time that the text event came in, in combination with a "Voice Activation Detection" (VAD) library gives us neatly cut audio.
+  * **Manual Trim**: If Automatic voiceline trim is not perfect, it's possible to [open the audio in an external program](https://youtu.be/LKFQFy2Qm64) for trimming.
+
+* **Screenshot**: Captures a screenshot of the game at the moment the voice line is spoken.
+
+* **Multi-Line**: It's possible to capture multiple lines at once with sentence audio with GSM's very own Texthooker.
+
+* **AI Translation**: Integrates AI to provide quick translations of the captured sentence. Custom Prompts also supported. (Optional, Bring your own Key)
+
+
+#### Game Example (Has Audio)
+
+https://github.com/user-attachments/assets/df6bc38e-d74d-423e-b270-8a82eec2394c
+
+---
+
+#### VN Example (Has Audio)
+
+https://github.com/user-attachments/assets/ee670fda-1a8b-4dec-b9e6-072264155c6e
+
+### OCR
+
+GSM runs a fork of [OwOCR](https://github.com/AuroraWright/owocr/) to provide accurate text capture from games that do not have a hook. Here are some improvements GSM makes on stock OwOCR:
+
+* **Easier Setup**: With GSM's managed Python install, setup is only a matter of clicking a few buttons.
+
+* **Exclusion Zones**: Instead of choosing an area to OCR, you can choose an area to exclude from OCR. Useful if you have a static interface in your game and text appears randomly throughout.
+
+* **Two-Pass OCR**: To cut down on API calls and keep output clean, GSM features a "Two-Pass" OCR System. A Local OCR will be constantly running, and when the text on screen stabilizes, it will run a second, more accurate scan that gets sent to clipboard/WebSocket.
+
+* **Consistent Audio Timing**: With the two-pass system, we can still get accurate audio recorded and into Anki without the use of crazy offsets or hacks.
+
+* **More Language Support**: Stock OwOCR is hard-coded to Japanese, while in GSM you can use a variety of languages.
+
+
+https://github.com/user-attachments/assets/07240472-831a-40e6-be22-c64b880b0d66
+
+
+
+### Game Launcher Capabilities (WIP)
+
+This is probably the feature I care least about, but if you are lazy like me, you may find this helpful.
+
+* **Launch**:  GSM can launch your games directly, simplifying the setup process.
+
+* **Hook**:  Streamlines the process of hooking your games (Agent).
+
+This feature simplifies the process of launching games and (potentially) hooking them, making the entire workflow more efficient.
+
+<img width="2560" height="1392" alt="GameSentenceMiner_1zuov0R9xK" src="https://github.com/user-attachments/assets/205769bb-3dd2-493b-9383-2d6e2ca05c2d" />
+
+## Basic Requirements
+
+* **Anki card creation tool**: [Yomitan](https://github.com/yomidevs/yomitan), [JL](https://github.com/rampaa/JL), etc.
+
+* **A method of getting text from the game**: [Agent](https://github.com/0xDC00/agent), [Textractor](https://github.com/Artikash/Textractor), [LunaTranslator](https://github.com/HIllya51/LunaTranslator), GSM's OCR, etc.
+
+* **A game :)**
+
+## Documentation
+
+For help with installation, setup, and other information, please visit the project's [Wiki](https://github.com/bpwhelan/GameSentenceMiner/wiki).
+
+## FAQ
+
+### How Does It Work?
+
+This is a common question, and understanding this process will help clarify any issues you might encounter while using GSM.
+
+1.  The beginning of the voice line is marked by a text event. This usually comes from Textractor, Agent, or another texthooker. GSM can listen for a clipboard copy and/or a WebSocket server (configurable in GSM).
+
+2.  The end of the voice line is detected using a Voice Activity Detection (VAD) library running locally. ([Example](https://github.com/snakers4/silero-vad))
+
+In essence, GSM relies on accurately timed text events to capture the corresponding audio.
+
+GSM provides settings to accommodate less-than-ideal hooks. However, if you experience significant audio inconsistencies, they likely stem from a poorly timed hook, loud background music, or other external factors, rather than GSM itself. The core audio trimming logic has been stable and effective for many users across various games.
+
+## Contact
+
+If you encounter issues, please ask for help in my [Discord](https://discord.gg/yP8Qse6bb8) or create an issue here.
+
+## Acknowledgements
+
+* [OwOCR](https://github.com/AuroraWright/owocr) for their outstanding OCR implementation, which I've integrated into GSM.
+
+* [chaiNNer](https://github.com/chaiNNer-org/chaiNNer) for the idea of installing Python within an Electron app.
+
+* [OBS](https://obsproject.com/) and [FFMPEG](https://ffmpeg.org/), without which GSM would not be possible.
+
+* [Renji's Texthooker](https://github.com/Renji-XD/texthooker-ui)
+
+* https://github.com/Saplling/transparent-texthooker-overlay
+
+## Donations
+
+If you've found this or any of my other projects helpful, please consider supporting my work through [GitHub Sponsors](https://github.com/sponsors/bpwhelan), or [Ko-fi](https://ko-fi.com/beangate).
+

{gamesentenceminer-2.14.5 → gamesentenceminer-2.14.7}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "GameSentenceMiner"
-version = "2.14.5"
+version = "2.14.7"
 description = "A tool for mining sentences from games. Update: Overlay?"
 readme = "README.md"
 requires-python = ">=3.10"

gamesentenceminer-2.14.5/GameSentenceMiner.egg-info/PKG-INFO

@@ -1,51 +0,0 @@
-Metadata-Version: 2.4
-Name: GameSentenceMiner
-Version: 2.14.5
-Summary: A tool for mining sentences from games. Update: Overlay?
-Author-email: Beangate <bpwhelan95@gmail.com>
-License: MIT License
-Project-URL: Homepage, https://github.com/bpwhelan/GameSentenceMiner
-Project-URL: Repository, https://github.com/bpwhelan/GameSentenceMiner
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: requests~=2.32.3
-Requires-Dist: watchdog~=5.0.2
-Requires-Dist: DateTime~=5.5
-Requires-Dist: pyperclip~=1.9.0
-Requires-Dist: soundfile~=0.12.1
-Requires-Dist: toml~=0.10.2
-Requires-Dist: psutil~=6.0.0
-Requires-Dist: rapidfuzz~=3.9.7
-Requires-Dist: plyer~=2.1.0
-Requires-Dist: keyboard~=0.13.5
-Requires-Dist: websockets~=15.0.1
-Requires-Dist: openai-whisper==20240930; sys_platform == "win32"
-Requires-Dist: openai-whisper; sys_platform != "win32"
-Requires-Dist: stable-ts-whisperless
-Requires-Dist: silero-vad~=5.1.2
-Requires-Dist: ttkbootstrap~=1.10.1
-Requires-Dist: dataclasses_json~=0.6.7
-Requires-Dist: win10toast; sys_platform == "win32"
-Requires-Dist: numpy==2.2.6
-Requires-Dist: pystray
-Requires-Dist: pywin32; sys_platform == "win32"
-Requires-Dist: pygetwindow; sys_platform == "win32"
-Requires-Dist: flask
-Requires-Dist: groq
-Requires-Dist: matplotlib
-Requires-Dist: sounddevice
-Requires-Dist: google-genai
-Requires-Dist: owocr
-Requires-Dist: oneocr
-Requires-Dist: openai
-Requires-Dist: scikit-image
-Requires-Dist: opencv-python
-Requires-Dist: betterproto==2.0.0b7
-Requires-Dist: obsws-python~=1.7.2
-Requires-Dist: numpy==2.2.6
-Requires-Dist: regex
-Dynamic: license-file

gamesentenceminer-2.14.5/PKG-INFO

@@ -1,51 +0,0 @@
-Metadata-Version: 2.4
-Name: GameSentenceMiner
-Version: 2.14.5
-Summary: A tool for mining sentences from games. Update: Overlay?
-Author-email: Beangate <bpwhelan95@gmail.com>
-License: MIT License
-Project-URL: Homepage, https://github.com/bpwhelan/GameSentenceMiner
-Project-URL: Repository, https://github.com/bpwhelan/GameSentenceMiner
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: requests~=2.32.3
-Requires-Dist: watchdog~=5.0.2
-Requires-Dist: DateTime~=5.5
-Requires-Dist: pyperclip~=1.9.0
-Requires-Dist: soundfile~=0.12.1
-Requires-Dist: toml~=0.10.2
-Requires-Dist: psutil~=6.0.0
-Requires-Dist: rapidfuzz~=3.9.7
-Requires-Dist: plyer~=2.1.0
-Requires-Dist: keyboard~=0.13.5
-Requires-Dist: websockets~=15.0.1
-Requires-Dist: openai-whisper==20240930; sys_platform == "win32"
-Requires-Dist: openai-whisper; sys_platform != "win32"
-Requires-Dist: stable-ts-whisperless
-Requires-Dist: silero-vad~=5.1.2
-Requires-Dist: ttkbootstrap~=1.10.1
-Requires-Dist: dataclasses_json~=0.6.7
-Requires-Dist: win10toast; sys_platform == "win32"
-Requires-Dist: numpy==2.2.6
-Requires-Dist: pystray
-Requires-Dist: pywin32; sys_platform == "win32"
-Requires-Dist: pygetwindow; sys_platform == "win32"
-Requires-Dist: flask
-Requires-Dist: groq
-Requires-Dist: matplotlib
-Requires-Dist: sounddevice
-Requires-Dist: google-genai
-Requires-Dist: owocr
-Requires-Dist: oneocr
-Requires-Dist: openai
-Requires-Dist: scikit-image
-Requires-Dist: opencv-python
-Requires-Dist: betterproto==2.0.0b7
-Requires-Dist: obsws-python~=1.7.2
-Requires-Dist: numpy==2.2.6
-Requires-Dist: regex
-Dynamic: license-file