Releases: 0Xiaohei0/VoiceToJapanese
VoiceToJapanese v1.2.6
VoiceToJapanese v1.2.6
Installation
- Download "python3.10" from the microsoft store
- Download "VoiceToJapanese-py.zip"
- Double click setup.bat
- If you encounter this error, install VS2019 redist by double clicking VC_redist.x64. Then double click setup.bat again.
- The program should start, from now on you can use start.bat to start the program more quickly.
If you encounter errors when running setup.bat, you can try the exe version in version 1.2.3 https://github.com/0Xiaohei0/VoiceToJapanese/releases/tag/v1.2.3
Noes: With the -py version you can inspect and make changes to all the python code and swap out libraries for running the AI models on GPU.
VoiceToJapanese v1.2.6 change notes:
- Added character ai support as an alternative to chatgpt. You can change the chcaracter by pasting the character id in settings. (How to get character id). You would need to log in by pasting the access token in settings for longer conversations (How to get access token).
- Added more input language support, setting input language to Auto would auto detect language.
- Added exclude user list for excluding certain user in stream chat. Put the list of excluded users in a text file called excluded_users.txt separated by enter key.
- Added ambient noise adjustment.
VoiceToJapanese v1.2.5
VoiceToJapanese v1.2.5
Installation
- Download "python3.10" from the microsoft store
- Download "VoiceToJapanese-py.zip"
- Double click setup.bat
- If you encounter this error, install VS2019 redist by double clicking VC_redist.x64. Then double click setup.bat again.
- The program should start, from now on you can use start.bat to start the program more quickly.
Noes: With the -py version you can inspect and make changes to all the python code and swap out libraries for running the AI models on GPU.
VoiceToJapanese v1.2.5 change notes:
- Added a cap to number of messages in chatbot request. If the stream is running for a long time, the messages will no longer overflow and fail the request.
VoiceToJapanese v1.2.4
VoiceToJapanese v1.2.4
Installation
- Download "python3.10" from the microsoft store
- Download "VoiceToJapanese-py.zip"
- Double click setup.bat
- If you encounter this error, install VS2019 redist by double clicking VC_redist.x64. Then double click setup.bat again.
- The program should start, from now on you can use start.bat to start the program more quickly.
Noes: With the -py version you can inspect and make changes to all the python code and swap out libraries for running the AI models on GPU.
VoiceToJapanese v1.2.4 change notes:
- Settings are now saved into a file called settings.json. The program will remember all your configurations in the settings tab even after you restart it. You can revert the settings to default by deleting settings.json
- Added support for games that force push to talk (valorant) The program will hold the "in-game push to talk key" when outputting audio.
- Added voice selection UI for elevenlab
VoiceToJapanese v1.2.3
VoiceToJapanese v1.2.3
Installation instructions:
1. Download "python3.10" from the microsoft store
2. Download "VoiceToJapanese.v1.2.3-py.zip" and run setup.bat.
3. If you encounter this error, install VS2019 redist by double clicking VC_redist.x64. Run setup.bat again.
4. The program should start, from now on you can use start.bat to start the program more quickly.
Noes: If you want to download an exe file, you can download the "VoiceToJapanese.v1.2.3-exe.zip" file and run the UI.exe inside. I would recommend downloading the -py version because anti-virus often report false-positive for .exe files. Additionally, with the version you can inspect and make changes to all the python code and swap out libraries for running the AI models on GPU.
VoiceToJapanese v1.2.3 change notes:
VoiceToJapanese v1.2.2
Installation instructions:
Download the zip file and run the UI.exe inside.
To use the chatbot functions you need to get an api key from open-ai: https://platform.openai.com/
You can put the api key in config.json or directly from the UI
VoiceToJapanese v1.2.2 change notes:
VoiceToJapanese v1.2.1
Installation instructions:
Download the zip file and run the UI.exe inside.
To use the chatbot functions you need to get an api key from open-ai: https://platform.openai.com/
then set it as an environment variable named OPENAI_API_KEY
VoiceToJapanese v1.2.1 change notes:
- Added integration with chatGPT, allowing you to hold a conversation with a chatbot ai. Demo video link: https://youtu.be/sz51Z4kdEHQ
- You can set the character setting in lore.txt
VoiceToJapanese v1.1.8
Installation instructions:
Download the zip file and run the UI.exe inside.
VoiceToJapanese v1.1.8 change notes:
VoiceToJapanese v1.1.7
Installation instructions:
Download the zip file and run the UI.exe inside.
VoiceToJapanese v1.1.7 change notes:
VoiceToJapanese v1.1.6
Installation instructions:
Download the zip file and run the UI.exe inside.
VoiceToJapanese v1.1.6 change notes:
-
Added subtitle generation with various options. You can change the audio source for subtitler through dropdown menu
-
Added options to use cloud ai providers (deepl and voicevox), you can provide your own deepl api key to use deepl translation on the cloud. You can also get voicevox on the cloud with or without api key. If you don't provide an API key, voicevox would be slower but can still be faster than running locally depending on your hardware. You can get voicevox api key here(free): https://su-shiki.com/api/
-
The problem of whisper not handling concurrent request is solved by separating recording and transcription into two different threads. The recording thread puts the recordings into a queue, the transcription thread continuously checks if the queue is empty, if it is not empty, remove the recording from the queue and transcribe. Writing subtitler this way prevents missing any audio while transcribing and ensures no concurrent requests are made.
-
fixed voice select bug where changing the speaker alone does not change the speaker id
-
filters out bad whisper output ('you', 'thank you.', 'thanks for watching.'). Whisper often recognizes background noise as these phrases. The filter is not configurable as of now.
-
translation model has been bundled with the program
-
Added check for CUDA status, however this does not work because the pytorch bundled with the program is CPU version, the GPU version is too big (4GB) for github
VoiceToJapanese v1.1.5
Installation instructions:
Download the zip file and run the UI.exe inside.
VoiceToJapanese v1.1.5 change notes:
- Moved translation to offline library.
- The program is now fully offline and can be ran with internet off.
- Translation model made by: https://huggingface.co/staka/fugumt-en-ja.