Direwolf Posted March 4 Posted March 4 I´ve installed the previous version of Whisper Attack (python, libraries, etc.).The new one overwrite the old one? Should I unzip the content over the already existent folder? If not, what should I do to with the previous version? Erase the whole folder? And about python, and the libraries? Is there a guide to uninstall the previous version before intall the new one?
sleighzy Posted March 4 Posted March 4 3 hours ago, Direwolf said: I´ve installed the previous version of Whisper Attack (python, libraries, etc.).The new one overwrite the old one? Should I unzip the content over the already existent folder? If not, what should I do to with the previous version? Erase the whole folder? And about python, and the libraries? Is there a guide to uninstall the previous version before intall the new one? You can delete the entire folder of your previous version. Python is no longer required for running this so that can be uninstalled if you wish. I’ll drop a command here for the folk who want to keep Python but no longer need the libraries we used. AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
Direwolf Posted March 4 Posted March 4 Almost there! I did everything pointed by the manual, but after dictating the command (Eg: "F1") i get these results: Starting Recording... Stoppped recording Raw transcribed text: 'F1' VoiceAttack not found so command will not be sent What is my mistake?
sleighzy Posted March 4 Posted March 4 (edited) 6 minutes ago, Direwolf said: Almost there! I did everything pointed by the manual, but after dictating the command (Eg: "F1") i get these results: Starting Recording... Stoppped recording Raw transcribed text: 'F1' VoiceAttack not found so command will not be sent What is my mistake? Have a look in your settings.cfg file and make sure the path and name is correctly pointing at where your VoiceAttack application is. This is for the voiceattack_location value. Edited March 4 by sleighzy AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
Direwolf Posted March 4 Posted March 4 Just now, sleighzy said: Have a look in your settings.cfg file and make sure the path and name is correctly pointing at where your VoiceAttack application is. Sorry! My mistake! The path was incorrect! Let me thank you for this app, because English is not my native language, so Voice Attack didnt´recognize a lot of my commands, but with your app, I have a very, very satisfactory answer. 1
sleighzy Posted March 7 Posted March 7 Some people have noted that their anti-virus has quarantined the WhisperAttack executable, this also happened for me this morning. This is a false positive and a known issue for some Python applications built using PyInstaller (which we use) or py2exe. You can add an exclusion to your antivirus software, e.g. Windows Defender, to prevent this from occurring. nullThere is another executable builder which apparently does not exhibit this issue so I will be investigating that for later releases. Apologies in advance if this has happened to you as well. 3 AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
sleighzy Posted March 17 Posted March 17 (edited) WhisperAttack v1.1.0 has just been released and now supports dark mode. Release v1.1.0 · nikoelt/WhisperAttack null Edited March 17 by sleighzy 2 1 AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
Redthyself Posted March 26 Posted March 26 Hey! Any chance I can also get an invite to the discord? Ive been trying to get a single command working to no avail. Ive installed the latest v1.1.0 release and followed the instructions the best I could. The whisperattack server recognizes what I say but this is all I get on voice attack. Im trying to use this with vaicom pro as well and looked at the integration instructions null
sleighzy Posted March 26 Posted March 26 (edited) On 3/27/2025 at 1:56 AM, Redthyself said: Hey! Any chance I can also get an invite to the discord? Ive been trying to get a single command working to no avail. Ive installed the latest v1.1.0 release and followed the instructions the best I could. The whisperattack server recognizes what I say but this is all I get on voice attack. Im trying to use this with vaicom pro as well and looked at the integration instructions null Discord channel link: https://discord.com/channels/610534461456777257/809527129422430218 Can you attach a screenshot of your WhisperAttack window as well as your C:\Users\username\AppData\Local\WhisperAttack\WhisperAttack.log file. Do you also have the Vaicom window open at the same time? If so then try closing the Vaicom Pro window, you can leave it running in the system tray. Edited April 21 by sleighzy 1 AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
sleighzy Posted March 28 Posted March 28 WhisperAttack v1.1.1 has now been released. Fixes & Improvements WhisperAttack now detects older GPUs that do not have Tensor cores and will default to a supported compute type for those GPUs The logging window now resizes to take up the width of the window when resizing it Fixed issue where fatal errors when WhisperAttack was running would not be displayed to users and would appear that WhisperAttack had hung Release v1.1.1 · nikoelt/WhisperAttack 2 1 AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
ScorpioFeralHog Posted April 8 Posted April 8 Is there a way to use WA with the TX-Link VOIP control?
sleighzy Posted April 9 Posted April 9 6 hours ago, ScorpioFeralHog said: Is there a way to use WA with the TX-Link VOIP control? Not at this stage. WA starts listening/recording when the tx button is pressed and stops when it is released. There is no functionality for a short press/release to start this, and then a subsequent short press/release to stop it. Broadcast Parallel is currently your only option. 1 AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
FredOfMBOX Posted May 3 Posted May 3 Thanks for this. WhisperAttack is a lot less frustrating that the default voice recognition. I have an issue, though. I keep getting output that ends in "--": Starting recording... Stopped recording Raw transcribed text: ' F1-- (static)' Sent text to VoiceAttack: F1 static Starting recording... Stopped recording Raw transcribed text: ' F1' Sent text to VoiceAttack: F1 Starting recording... Stopped recording Raw transcribed text: ' Communication menu' Sent text to VoiceAttack: Communication menu Starting recording... Stopped recording Raw transcribed text: ' Communications menu--' Sent text to VoiceAttack: Communications menu-- Starting recording... Stopped recording Raw transcribed text: ' Communications menu--' Sent text to VoiceAttack: Communications menu-- Starting recording... Stopped recording Raw transcribed text: ' Communications menu--' Sent text to VoiceAttack: Communications menu-- Starting recording... Stopped recording Raw transcribed text: ' Communications menu--' Sent text to VoiceAttack: Communications menu-- It's not every time, but it's frequent. I could go into my VA profile and add `--` as an optional alternate, but I'd rather avoid that if possible. Any thoughts?
sleighzy Posted May 3 Posted May 3 (edited) @FredOfMBOX Definitely looks like a bug. I’ll have a look into it. If you’re getting it consistently with menu— (and other words) you could try adding the below into the word_mappings.txt file to workaround it for now. menu--=menu 59 minutes ago, sleighzy said: Definitely looks like a bug. I’ll have a look into it. If you’re getting it consistently with menu— (and other words) you could try adding the below into the word_mappings.txt file to workaround it for now. menu--=menu EDIT: try just applying this as a blanket thing to see if this handles it. --= I’m not around for a couple of days to confirm the above blanket approach, but give it a shot. Edited May 3 by sleighzy AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
sleighzy Posted May 4 Posted May 4 I've made a fix for this to better handle on our end, no idea why the OpenAI Whisper model transcribes it this way. Will be available in a future release. The workaround should hopefully suffice for now. 1 AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
Fox-one-76 Posted May 21 Posted May 21 Hello, i am having a strange issue with whisper attack.... when i test it with Voice attack + VAICOM, all is fine, the voice recognition manages to recognize almost every thing despite my french accent.... but when i start DCS then it stops working.... no voice seems to be recorded by whisper attack, i am still hearing the static noise from voice attack telling me when the PTT button is pressed and also when depressed... but nothing is recognized, because nothing is transmitted by WA to VA ... the logs shows that when this happens Whisper is looking for a wav file and finds one that is always 80KB no matter the length of what i am saying... Quote 2025-05-21 22:03:50,113 - INFO - Received command: start 2025-05-21 22:03:50,113 - INFO - Starting recording... 2025-05-21 22:03:50,118 - INFO - Received command: stop 2025-05-21 22:03:50,118 - INFO - Stopping recording... 2025-05-21 22:03:50,170 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:03:50,170 - INFO - File exists, size = 80 bytes 2025-05-21 22:03:50,170 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:03:50,207 - INFO - Processing audio with duration 00:00.000 2025-05-21 22:03:50,208 - INFO - Raw transcription result: '' 2025-05-21 22:03:50,209 - INFO - No transcription result. Here is the full log in it there are some attempts with and without DCS running. Quote 2025-05-21 21:54:22,099 - INFO - Loaded configuration: {'whisper_model': 'small.en', 'whisper_device': 'GPU', 'voiceattack_location': 'C:\\Program Files (x86)\\VoiceAttack\\VoiceAttack.exe', 'theme': 'default'} 2025-05-21 21:54:22,147 - INFO - Loaded word mappings: {'gulf': 'Golf', 'gold': 'Golf', 'atel': 'Hotel', 'leema': 'Lima', 'mic': 'Mike', 'Cubac': 'Quebec', 'wosky': 'Whiskey', 'weske': 'Whiskey', 'tawa': 'Tower', 'inter': 'Enter', 'take-off': 'takeoff', 'pre-contact': 'precontact'} 2025-05-21 21:54:22,181 - INFO - Loading Whisper model (small.en), device=GPU, core_type=tensor ... 2025-05-21 21:54:27,770 - INFO - GPU has cuda capability major=8 minor=9 2025-05-21 21:54:28,882 - INFO - Successfully loaded Whisper model 2025-05-21 21:54:28,884 - INFO - Server started and listening on 127.0.0.1:65432 2025-05-21 21:56:54,283 - INFO - Received command: start 2025-05-21 21:56:54,283 - INFO - Starting recording... 2025-05-21 21:56:54,651 - INFO - Received command: stop 2025-05-21 21:56:54,651 - INFO - Stopping recording... 2025-05-21 21:56:54,690 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 21:56:54,690 - INFO - File exists, size = 21712 bytes 2025-05-21 21:56:54,690 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 21:56:54,738 - INFO - Processing audio with duration 00:00.338 2025-05-21 21:57:13,454 - INFO - Raw transcription result: ' (buzzing)' 2025-05-21 21:57:13,455 - INFO - Cleaned transcription: buzzing 2025-05-21 21:57:13,455 - INFO - Fuzzy-corrected transcription: buzzing 2025-05-21 21:57:13,455 - INFO - Sending recognized text to VoiceAttack: buzzing 2025-05-21 21:57:13,717 - INFO - Received command: start 2025-05-21 21:57:13,717 - INFO - Starting recording... 2025-05-21 21:57:13,722 - INFO - Received command: stop 2025-05-21 21:57:13,722 - INFO - Stopping recording... 2025-05-21 21:57:13,775 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 21:57:13,775 - INFO - File exists, size = 80 bytes 2025-05-21 21:57:13,775 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 21:57:13,811 - INFO - Processing audio with duration 00:00.000 2025-05-21 21:57:13,812 - INFO - Raw transcription result: '' 2025-05-21 21:57:13,813 - INFO - No transcription result. 2025-05-21 21:57:13,813 - INFO - Received command: start 2025-05-21 21:57:13,813 - INFO - Starting recording... 2025-05-21 21:57:13,818 - INFO - Received command: stop 2025-05-21 21:57:13,818 - INFO - Stopping recording... 2025-05-21 21:57:13,871 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 21:57:13,871 - INFO - File exists, size = 80 bytes 2025-05-21 21:57:13,871 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 21:57:13,910 - INFO - Processing audio with duration 00:00.000 2025-05-21 21:57:13,911 - INFO - Raw transcription result: '' 2025-05-21 21:57:13,911 - INFO - No transcription result. 2025-05-21 21:57:13,912 - INFO - Received command: start 2025-05-21 21:57:13,912 - INFO - Starting recording... 2025-05-21 21:57:13,917 - INFO - Received command: stop 2025-05-21 21:57:13,917 - INFO - Stopping recording... 2025-05-21 21:57:13,969 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 21:57:13,969 - INFO - File exists, size = 80 bytes 2025-05-21 21:57:13,969 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 21:57:14,001 - INFO - Processing audio with duration 00:00.000 2025-05-21 21:57:14,002 - INFO - Raw transcription result: '' 2025-05-21 21:57:14,002 - INFO - No transcription result. 2025-05-21 22:02:00,502 - INFO - Received command: start 2025-05-21 22:02:00,506 - INFO - Starting recording... 2025-05-21 22:02:04,883 - INFO - Received command: stop 2025-05-21 22:02:04,883 - INFO - Stopping recording... 2025-05-21 22:02:04,923 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:02:04,923 - INFO - File exists, size = 277968 bytes 2025-05-21 22:02:04,923 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:02:05,078 - INFO - Processing audio with duration 00:04.342 2025-05-21 22:03:49,169 - INFO - Raw transcription result: ' Insert request startup' 2025-05-21 22:03:49,171 - INFO - Cleaned transcription: Insert request startup 2025-05-21 22:03:49,171 - INFO - Fuzzy-corrected transcription: Insert request startup 2025-05-21 22:03:49,171 - INFO - Sending recognized text to VoiceAttack: Insert request startup 2025-05-21 22:03:49,515 - INFO - Received command: start 2025-05-21 22:03:49,515 - INFO - Starting recording... 2025-05-21 22:03:49,522 - INFO - Received command: stop 2025-05-21 22:03:49,522 - INFO - Stopping recording... 2025-05-21 22:03:49,574 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:03:49,574 - INFO - File exists, size = 80 bytes 2025-05-21 22:03:49,574 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:03:49,619 - INFO - Processing audio with duration 00:00.000 2025-05-21 22:03:49,620 - INFO - Raw transcription result: '' 2025-05-21 22:03:49,621 - INFO - No transcription result. 2025-05-21 22:03:49,622 - INFO - Received command: start 2025-05-21 22:03:49,622 - INFO - Starting recording... 2025-05-21 22:03:49,627 - INFO - Received command: stop 2025-05-21 22:03:49,627 - INFO - Stopping recording... 2025-05-21 22:03:49,680 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:03:49,680 - INFO - File exists, size = 80 bytes 2025-05-21 22:03:49,680 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:03:49,718 - INFO - Processing audio with duration 00:00.000 2025-05-21 22:03:49,719 - INFO - Raw transcription result: '' 2025-05-21 22:03:49,720 - INFO - No transcription result. 2025-05-21 22:03:49,722 - INFO - Received command: start 2025-05-21 22:03:49,722 - INFO - Starting recording... 2025-05-21 22:03:49,727 - INFO - Received command: stop 2025-05-21 22:03:49,727 - INFO - Stopping recording... 2025-05-21 22:03:49,781 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:03:49,781 - INFO - File exists, size = 80 bytes 2025-05-21 22:03:49,781 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:03:49,815 - INFO - Processing audio with duration 00:00.000 2025-05-21 22:03:49,816 - INFO - Raw transcription result: '' 2025-05-21 22:03:49,817 - INFO - No transcription result. 2025-05-21 22:03:49,819 - INFO - Received command: start 2025-05-21 22:03:49,819 - INFO - Starting recording... 2025-05-21 22:03:49,824 - INFO - Received command: stop 2025-05-21 22:03:49,824 - INFO - Stopping recording... 2025-05-21 22:03:49,877 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:03:49,877 - INFO - File exists, size = 80 bytes 2025-05-21 22:03:49,877 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:03:49,913 - INFO - Processing audio with duration 00:00.000 2025-05-21 22:03:49,914 - INFO - Raw transcription result: '' 2025-05-21 22:03:49,916 - INFO - No transcription result. 2025-05-21 22:03:49,917 - INFO - Received command: start 2025-05-21 22:03:49,917 - INFO - Starting recording... 2025-05-21 22:03:49,923 - INFO - Received command: stop 2025-05-21 22:03:49,923 - INFO - Stopping recording... 2025-05-21 22:03:49,976 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:03:49,976 - INFO - File exists, size = 80 bytes 2025-05-21 22:03:49,976 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:03:50,011 - INFO - Processing audio with duration 00:00.000 2025-05-21 22:03:50,012 - INFO - Raw transcription result: '' 2025-05-21 22:03:50,014 - INFO - No transcription result. 2025-05-21 22:03:50,015 - INFO - Received command: start 2025-05-21 22:03:50,015 - INFO - Starting recording... 2025-05-21 22:03:50,020 - INFO - Received command: stop 2025-05-21 22:03:50,020 - INFO - Stopping recording... 2025-05-21 22:03:50,074 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:03:50,074 - INFO - File exists, size = 80 bytes 2025-05-21 22:03:50,074 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:03:50,109 - INFO - Processing audio with duration 00:00.000 2025-05-21 22:03:50,110 - INFO - Raw transcription result: '' 2025-05-21 22:03:50,111 - INFO - No transcription result. 2025-05-21 22:03:50,113 - INFO - Received command: start 2025-05-21 22:03:50,113 - INFO - Starting recording... 2025-05-21 22:03:50,118 - INFO - Received command: stop 2025-05-21 22:03:50,118 - INFO - Stopping recording... 2025-05-21 22:03:50,170 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:03:50,170 - INFO - File exists, size = 80 bytes 2025-05-21 22:03:50,170 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:03:50,207 - INFO - Processing audio with duration 00:00.000 2025-05-21 22:03:50,208 - INFO - Raw transcription result: '' 2025-05-21 22:03:50,209 - INFO - No transcription result. 2025-05-21 22:04:35,333 - INFO - Received command: start 2025-05-21 22:04:35,333 - INFO - Starting recording... 2025-05-21 22:04:38,506 - INFO - Received command: stop 2025-05-21 22:04:38,506 - INFO - Stopping recording... 2025-05-21 22:04:38,558 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:04:38,558 - INFO - File exists, size = 201424 bytes 2025-05-21 22:04:38,558 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:04:38,601 - INFO - Processing audio with duration 00:03.146 2025-05-21 22:05:01,082 - INFO - Raw transcription result: ' Request start-up' 2025-05-21 22:05:01,086 - INFO - Cleaned transcription: Request start-up 2025-05-21 22:05:01,086 - INFO - Fuzzy-corrected transcription: Request start-up 2025-05-21 22:05:01,086 - INFO - Sending recognized text to VoiceAttack: Request start-up 2025-05-21 22:05:01,388 - INFO - Received command: start 2025-05-21 22:05:01,388 - INFO - Starting recording... 2025-05-21 22:05:01,398 - INFO - Received command: stop 2025-05-21 22:05:01,398 - INFO - Stopping recording... 2025-05-21 22:05:01,451 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:05:01,451 - INFO - File exists, size = 80 bytes 2025-05-21 22:05:01,451 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:05:01,487 - INFO - Processing audio with duration 00:00.000 2025-05-21 22:05:01,488 - INFO - Raw transcription result: '' 2025-05-21 22:05:01,492 - INFO - No transcription result. 2025-05-21 22:05:01,499 - INFO - Received command: start 2025-05-21 22:05:01,499 - INFO - Starting recording... 2025-05-21 22:05:01,510 - INFO - Received command: stop 2025-05-21 22:05:01,510 - INFO - Stopping recording... 2025-05-21 22:05:01,577 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:05:01,577 - INFO - File exists, size = 80 bytes 2025-05-21 22:05:01,577 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:05:01,612 - INFO - Processing audio with duration 00:00.000 2025-05-21 22:05:01,613 - INFO - Raw transcription result: '' 2025-05-21 22:05:01,617 - INFO - No transcription result. 2025-05-21 22:05:15,462 - INFO - Received command: start 2025-05-21 22:05:15,462 - INFO - Starting recording... 2025-05-21 22:05:17,840 - INFO - Received command: stop 2025-05-21 22:05:17,840 - INFO - Stopping recording... 2025-05-21 22:05:17,899 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:05:17,899 - INFO - File exists, size = 151504 bytes 2025-05-21 22:05:17,899 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:05:17,936 - INFO - Processing audio with duration 00:02.366 2025-05-21 22:05:18,019 - INFO - Raw transcription result: ' Request startup' 2025-05-21 22:05:18,023 - INFO - Cleaned transcription: Request startup 2025-05-21 22:05:18,023 - INFO - Fuzzy-corrected transcription: Request startup 2025-05-21 22:05:18,023 - INFO - Sending recognized text to VoiceAttack: Request startup 2025-05-21 22:05:24,464 - INFO - Received command: start 2025-05-21 22:05:24,465 - INFO - Starting recording... 2025-05-21 22:05:28,293 - INFO - Received command: stop 2025-05-21 22:05:28,293 - INFO - Stopping recording... 2025-05-21 22:05:28,328 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:05:28,328 - INFO - File exists, size = 243024 bytes 2025-05-21 22:05:28,328 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:05:28,385 - INFO - Processing audio with duration 00:03.796 2025-05-21 22:05:28,505 - INFO - Raw transcription result: ' Incirlik request startup' 2025-05-21 22:05:28,509 - INFO - Cleaned transcription: Incirlik request startup 2025-05-21 22:05:28,509 - INFO - Fuzzy-corrected transcription: Incirlik request startup 2025-05-21 22:05:28,509 - INFO - Sending recognized text to VoiceAttack: Incirlik request startup 2025-05-21 22:05:37,114 - INFO - Received command: start 2025-05-21 22:05:37,114 - INFO - Starting recording... 2025-05-21 22:05:37,438 - INFO - Received command: stop 2025-05-21 22:05:37,438 - INFO - Stopping recording... 2025-05-21 22:05:37,485 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:05:37,485 - INFO - File exists, size = 20048 bytes 2025-05-21 22:05:37,485 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:05:37,519 - INFO - Processing audio with duration 00:00.312 2025-05-21 22:05:37,618 - INFO - Raw transcription result: ' (buzzing)' 2025-05-21 22:05:37,622 - INFO - Cleaned transcription: buzzing 2025-05-21 22:05:37,622 - INFO - Fuzzy-corrected transcription: buzzing 2025-05-21 22:05:37,622 - INFO - Sending recognized text to VoiceAttack: buzzing 2025-05-21 22:05:44,028 - INFO - Received command: start 2025-05-21 22:05:44,028 - INFO - Starting recording... 2025-05-21 22:05:44,539 - INFO - Received command: stop 2025-05-21 22:05:44,539 - INFO - Stopping recording... 2025-05-21 22:05:44,597 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:05:44,597 - INFO - File exists, size = 31696 bytes 2025-05-21 22:05:44,597 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:05:44,629 - INFO - Processing audio with duration 00:00.494 2025-05-21 22:05:44,726 - INFO - Raw transcription result: ' (buzzing)' 2025-05-21 22:05:44,730 - INFO - Cleaned transcription: buzzing 2025-05-21 22:05:44,730 - INFO - Fuzzy-corrected transcription: buzzing 2025-05-21 22:05:44,730 - INFO - Sending recognized text to VoiceAttack: buzzing 2025-05-21 22:05:48,394 - INFO - Received command: start 2025-05-21 22:05:48,394 - INFO - Starting recording... 2025-05-21 22:05:53,309 - INFO - Received command: stop 2025-05-21 22:05:53,309 - INFO - Stopping recording... 2025-05-21 22:05:53,352 - INFO - Checking if file exists: C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav 2025-05-21 22:05:53,352 - INFO - File exists, size = 312912 bytes 2025-05-21 22:05:53,352 - INFO - Transcribing C:\Users\UTILIS~1\AppData\Local\Temp\whisper_temp_recording.wav... 2025-05-21 22:05:53,385 - INFO - Processing audio with duration 00:04.888 2025-05-21 22:05:53,534 - INFO - Raw transcription result: ' Incirlik - Enfield11 - Request startup' 2025-05-21 22:05:53,538 - INFO - Cleaned transcription: Incirlik Enfield11 Request startup 2025-05-21 22:05:53,539 - INFO - Fuzzy-corrected transcription: Incirlik Enfield11 Request startup 2025-05-21 22:05:53,539 - INFO - Sending recognized text to VoiceAttack: Incirlik Enfield11 Request startup Thanks for any help you can provide...
sleighzy Posted May 22 Posted May 22 (edited) 4 hours ago, Fox-one-76 said: Hello, i am having a strange issue with whisper attack.... when i test it with Voice attack + VAICOM, all is fine, the voice recognition manages to recognize almost every thing despite my french accent.... but when i start DCS then it stops working.... no voice seems to be recorded by whisper attack, i am still hearing the static noise from voice attack telling me when the PTT button is pressed and also when depressed... but nothing is recognized, because nothing is transmitted by WA to VA ... the logs shows that when this happens Whisper is looking for a wav file and finds one that is always 80KB no matter the length of what i am saying... Here is the full log in it there are some attempts with and without DCS running. Thanks for any help you can provide... I’m away for a couple of days so can’t dig in too much right now sorry. Can you confirm that you don’t have the radios bound to your hotas in the DCS controls settings for that plane. Based on that log for 80bytes the stop command looks to be occurring at the same time, or a few milliseconds after the start command. Can you drop a screenshot of your VA Vaicom profile that is expanded to show all the press and release plugin actions for your tx buttons. Can you also let me know which plane and tx button you’re using On a side note, in your last couple of commands you won’t need (and VA won’t recognize) using the sender in the command, eg Enfield11 Edited May 22 by sleighzy AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
sleighzy Posted May 22 Posted May 22 Can you also enable the debug flag in Vaicom and the VA window will then show when the tx button is pressed and released. With DCS running, but viewing the VA window, can you see if holding down the mic button and talking shows the tx press line, but doesn’t show the tx release line until you finish talking and release it…or if the release is being triggered immediately. AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
Fox-one-76 Posted May 22 Posted May 22 nullnullnullHi, here are the screenshots yes when i hold down the PTT button i see it recorded in Voice Attack TX1 press / TX1 release and it matches with when i press / release them I have tested in both MB339A and C101CC I use the same buttons (on my hotas throttle) and those buttons are not mapped to anything in DCS , they only serve for Voice attack hope this helps
VirusAM Posted May 25 Posted May 25 (edited) Hi...I just started using this new integration. I use it with Vaicom...I read all the instructions and applied it to my system. I have a couple of issues: a) When I am with the open whisper and vaicom windows in focus commands are sent into DCS. When DCS have the focus this integration doesn't work. So is this something that other users saw or just my particular case? In the uploaded picture you can see a couple of examples. b) The recognition is not particularly better than the Voice Attack speech default speech recognition. There you normally train it. Is there any way to improve recognition for non native english speaker using this model? Thanks PICTURE EXPLANATION 0) ready pre contact is recognized by whisper attack but not sent to Vaicom and DCS. and in the end I need to use the keyboard 1) "Tanker Approacching for refuel" is recognized and then again not sent to Vaicom and DCS. 2) Now I switched focus to the Whisper Attack window with alt-tab (so dcs is in background) and "Tanker Approacching for refuel" is sent to vaicom and then DCS..so also the DCS radio sent the request for refuel to the tanker. Thanks everyone for attention Edited May 25 by VirusAM R7-5800X3D 64GB RTX-4090 LG-38GN950 N/A Realsimulator FFSB MKII Ultra+F-16 grip+F/A-18 grip, VKB Stecs Max, VKB T-Rudder MKV, Razer Tartarus V2 Secrets Lab Tytan, Monstertech ChairMounts
VirusAM Posted May 25 Posted May 25 On 5/22/2025 at 3:52 AM, sleighzy said: I’m away for a couple of days so can’t dig in too much right now sorry. Can you confirm that you don’t have the radios bound to your hotas in the DCS controls settings for that plane. Based on that log for 80bytes the stop command looks to be occurring at the same time, or a few milliseconds after the start command. Can you drop a screenshot of your VA Vaicom profile that is expanded to show all the press and release plugin actions for your tx buttons. Can you also let me know which plane and tx button you’re using On a side note, in your last couple of commands you won’t need (and VA won’t recognize) using the sender in the command, eg Enfield11 Similar issue to what is reported here....Like if when whisper attack is not in focus it doens't send commands to voice attack R7-5800X3D 64GB RTX-4090 LG-38GN950 N/A Realsimulator FFSB MKII Ultra+F-16 grip+F/A-18 grip, VKB Stecs Max, VKB T-Rudder MKV, Razer Tartarus V2 Secrets Lab Tytan, Monstertech ChairMounts
VirusAM Posted May 25 Posted May 25 (edited) Similar example here... first "flight go to tanker" is not sent to vaicom and dcs second one is sent... only difference is that in the first time I was in DCS, the second time I was with Open Whisper window in focus and DCS in the background Edited May 25 by VirusAM R7-5800X3D 64GB RTX-4090 LG-38GN950 N/A Realsimulator FFSB MKII Ultra+F-16 grip+F/A-18 grip, VKB Stecs Max, VKB T-Rudder MKV, Razer Tartarus V2 Secrets Lab Tytan, Monstertech ChairMounts
sleighzy Posted May 25 Posted May 25 (edited) 4 hours ago, VirusAM said: Hi...I just started using this new integration. I use it with Vaicom...I read all the instructions and applied it to my system. I have a couple of issues: a) When I am with the open whisper and vaicom windows in focus commands are sent into DCS. When DCS have the focus this integration doesn't work. So is this something that other users saw or just my particular case? In the uploaded picture you can see a couple of examples. b) The recognition is not particularly better than the Voice Attack speech default speech recognition. There you normally train it. Is there any way to improve recognition for non native english speaker using this model? Thanks PICTURE EXPLANATION 0) ready pre contact is recognized by whisper attack but not sent to Vaicom and DCS. and in the end I need to use the keyboard 1) "Tanker Approacching for refuel" is recognized and then again not sent to Vaicom and DCS. 2) Now I switched focus to the Whisper Attack window with alt-tab (so dcs is in background) and "Tanker Approacching for refuel" is sent to vaicom and then DCS..so also the DCS radio sent the request for refuel to the tanker. Thanks everyone for attention Hi @VirusAM. Can you enable debug within Vaicom and then replicate this issue and then drop your C:\Users\username\AppData\Local\WhisperAttack\WhisperAttack.log file here. Please also provide a screenshot from VoiceAttack so I can see the full output from the debug. Can you also ensure that the Vaicom window is closed, i.e. completely closed so that it is just in the system tray. Can you also try this by updating your settings.cfg file in WhisperAttack so that the whisper model used is tiny.en (I think it's small.en by default). I see in your screenshot the message "PTT: use an active TX node" when this occurs. Vaicom has a timeout from when you release the tx button till it receives the actual command. This means that VoiceAttack gets the command, sends it to Vaicom, but due to it taking too long it won't do anything in the game. It seems like maybe there is a timing issue and it is taking too long from when WhisperAttack hears your command until VoiceAttack processes it after you release the button. What video card do you have? I have only seen this with one user before, it seemed to be a VoiceAttack issue of some description at the time. Are you on VoiceAttack v1 or v2? There is a profile tweak we can make that may help but would be good to see the whisper attack log file for this issue first to confirm. You also mentioned that the default Windows speech engine works just as well for you as WhisperAttack. If that engine is working for you then WhisperAttack may not be needed, this was just beneficial for users for whom the Windows one doesn't work well. There is no ability to train this whisper model. Edited May 25 by sleighzy AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
sleighzy Posted May 25 Posted May 25 (edited) On 5/23/2025 at 7:23 AM, Fox-one-76 said: nullnullnullHi, here are the screenshots yes when i hold down the PTT button i see it recorded in Voice Attack TX1 press / TX1 release and it matches with when i press / release them I have tested in both MB339A and C101CC I use the same buttons (on my hotas throttle) and those buttons are not mapped to anything in DCS , they only serve for Voice attack hope this helps One thing I noticed here from your screenshot was the message that multiple Vaicom plugins were found. Can you check your VAICOM installation and make sure you have only one in VoiceAttack apps and there is only a single dll file. null You also appear to have the "PTT: Use an active TX node" message similar to the other user, I don't know if this is related...although your issue is slightly different.null Edited May 25 by sleighzy AMD 7800x3D, 4080Super, 64Gb DDR5 RAM, 4Tb NVMe M.2, Quest 2
Recommended Posts