You can find many useful links in Menu Bar -- Help/About, such as model download addresses and CUDA configuration. Try clicking on them when you encounter problems.

1. Cannot Open After Double-Clicking sp.exe

The software is developed based on pyside6. The main interface uses many Qt components, so loading might be slow, ranging from 5 seconds to 2 minutes. Please be patient.

If it still doesn't fully display after a few minutes, with only a black window instead of the startup screen, there might be an error. Check the console for error messages. If you downloaded the pre-packaged version, make sure you downloaded the complete package, not just the update.

If all methods fail and it still won't open after a long wait, open the latest log file in the logs folder, check the error information, or submit the file to GitHub Issue or bbs.pyvideotrans.com to ask questions and upload the file.

2. Video Clarity Reduced

Some operations during translation involve transcoding, which inevitably leads to quality loss. To minimize this loss, you can do the following:

1. Use original videos encoded with libx264 in MP4 format.
2. Set the following in Menu -- Tools -- Advanced Settings:

3. Error During Translation Phase

If a red error message appears during the translation process after the subtitles are recognized, it's usually due to a "network connection error" or an "account issue" with the translation channel you are using.

If you are using "Google," "Microsoft," or "Gemini" as your translation channel, it's likely a network connection issue. You need to enable a VPN and fill in the network proxy address provided by your VPN tool in the network proxy address text box.

If you are using a VPN but still get a network connection error, your proxy might be unavailable. Please correctly enter the HTTP proxy IP and port number provided by your VPN tool.

If you are sure the proxy is available but still get an error, it's likely that the account is unavailable. For example, Gemini is not available in all countries. You can try switching the proxy node to another country.

Gemini, ChatGPT, and AzureGPT channels generally have request frequency limits. Excluding network and account issues, the request frequency might have exceeded the limit. At this point, you can open Menu -- Tools -- Advanced Settings and set "Pause Time After Translation /s" to 30 or a larger number.

3. Speech Recognition Accuracy Too Low

1. In faster mode and openai mode, using larger models can improve accuracy. tiny is a small model with poor recognition, while large-v3 is the largest model with the best recognition. All model download addresses: https://pyvideotrans.com/model
2. If the original video is in Chinese, try using zh_recogn for better results. Instructions: https://pyvideotrans.com/zh_recogn.html
3. Select "Keep Background Sound" to denoise in advance for better recognition, but be careful not to select this option if the video is very large.

4. Model Download Address

Model download address: https://pyvideotrans.com/model

5. Is it Available on Win7?

Win7 is not supported.

6. Prompt: Missing python310.dll

You may have only downloaded the upgrade patch package. The patch package cannot be used alone. Please download the full 1.9G package first, and then download the patch package to overwrite it after decompression.

7. Error During Merging Phase ffprobe {}

It is very likely that the spaces or single/double quotes in the original video name are causing the problem. Try renaming the original video. For example, if the original name is D:/UNSW/2024 T2/BIOS 2061/Week 5 Amphibians, reptiles, and birds/_video_out/BIOS2061-5246_00069- Lecture 13 - Birds 1 'Origin of Birds' - Prof. Richard Kingsford- Part 2 - UNSW##BIOS2061-5246_00069- Lecture 13 - Birds 1 'Origin of Birds' - Prof. Richard Kingsford- Part 2 - UNSW.mp4, you can see that the video name is very complex and contains spaces, single quotes, etc. This type of name is very prone to errors during processing. Please delete spaces, single quotes.

Is Docker Deployment Supported?

No.

Can it Recognize Subtitle Text in Videos, i.e., OCR Recognition?

The software works by recognizing human speech in videos and converting it into text subtitles. It does not support OCR subtitle recognition.

Can it be Called Through HTTP API Interface?

Not currently, but this feature may be added later.

Can New Languages Be Added?

No, because speech recognition for subtitles relies on the Whisper model, which supports a limited number of languages. Unsupported languages cannot be recognized.

Where to Download the Software?

https://pyvideotrans.com/downpackage.html

Where to Download the Models?

https://pyvideotrans.com/model.html

I Have Installed CUDA, But Still Cannot Use it

Possible reasons:

1. Built-in CUDA support requires version 11.8 or above. Check if your CUDA version is too low.
2. The graphics card driver is too old and needs to be updated.
3. cudnn is not installed.
4. The graphics card is not an NVIDIA card or is incompatible.

Does it Support Multi-Role Recognition and Voiceover?

No, the recognized subtitles do not distinguish between speakers and roles. This function can be manually implemented by "setting line roles".

CLI Command Line Mode Always Has Problems

CLI method updates are lagging, please use the old version.

Error During Translation Phase

Please change the translation channel or fill in the network proxy.

Software Freezes and Does Not Start After Double-Clicking, Stuck on the Startup Screen

The software is relatively large, please be patient. If it still does not open after a long time, please try:

1. Close antivirus software, security software, etc.
2. Confirm that the path and directory where the software is located are composed of English or numbers, and do not contain spaces, Chinese, special symbols, etc.

If it fails to start after overwriting the upgrade package, please download the complete package.

If it is already a complete package, please be patient. If it still doesn't start after more than 2 minutes, try force-closing and reopening.

Which Translations are Supported?

Currently supports Microsoft Translator, Google Translate, Baidu Translate, Tencent Translate, DeepL Translate, ChatGPT Translate, AzureGPT Translate, Gemini Pro Translate, DeepLx Translate, OTT Offline Translation, FreeGoogle Translate, FreeChatGPT Translate.

Connection error

The error Connection error indicates that the network connection failed. If you have not filled in a proxy in the software interface, please fill it in. You cannot directly connect to ChatGPT/Gemini/Google APIs in China. You need to fill in a proxy. Note that being able to open the corresponding website in the browser does not mean that it can be used in the software. Please fill in the correct proxy address in the network proxy input box.

Whole all out of memory

The error Whole all out of memory indicates that there is insufficient video memory. Please use a smaller model, such as tiny or small.

Requested float16 compute type, but the target device or backend do not support efficient float 16 computation

The error shows that the current graphics card does not support this data type. The solution is to open Menu -- Tools -- Advanced Settings, find

CUDA Data Type

Change the content to int8_float16

Then restart the software and execute. If the error still occurs, change it to

float32

How to Install

No installation is required. After downloading the complete package and decompressing it, double-click sp.exe to use it.

Why is it Reported as a Virus or Blocked?

This is software packaged using pyinstaller. It has not been digitally signed or certified by anti-virus software, so it may be falsely reported. Please add it to the trusted whitelist or close the security software. Or use source code deployment.

Which TTS Voiceovers are Supported?

edgeTTS / Azure AI / GPT-SoVITS / clone-voice / elevenlabs

Source Code Deployment Issues

1. The default uses ctranslate2 version 4.x, which only supports CUDA 12.x. If your CUDA version is lower than 12 and you cannot upgrade CUDA to 12.x, please execute the command to uninstall ctranslate2 and then reinstall it

pip uninstall -y ctranslate2
pip install ctranslate2==3.24.0

2. You may encounter errors such as xx module not found. Please open requirements.txt, search for the xx module, and then remove the == and the version number after xx.

Is there any customer service?

No, this is free software, there is no income and no profit, and it is impossible to equip customer service.

Is there a charge?

This is a free and open source project, and does not charge any fees. Free to use. Translation and tts interfaces are charged by their respective API merchants, which has nothing to do with this project

Can it be used commercially?

Individuals or companies can use it casually. However, if you want to integrate it into a commercial project, please follow the GPL-v3 open source protocol