General Introduction
AsrTools is a smart speech-to-text tool with built-in interfaces from big players like Cutscene, Fast, Must Cut, etc. It supports efficient multi-threaded batch processing without GPU or cumbersome configuration. It is developed based on PyQt5, with a beautiful and user-friendly interface, capable of outputting SRT and TXT format subtitle files. The tool processes audio files in the cloud by calling big-factory interfaces and provides stable and fast text conversion services, suitable for users who need to efficiently process audio to text.
Function List
- Calling the big factory interface: support clipping, fast hand, must cut and other big factory interface, to provide high-quality services
- No need for complex configurations: no GPU and cumbersome local configurations, users can easily get started
- High-value interface: Based on PyQt5 and qfluentwidgets, the interface is beautiful and user-friendly.
- Efficient batch processing: supports multi-threaded concurrent and batch processing, fast text conversion speed
- Multi-format support: support for generating SRT and TXT subtitle files to meet different needs
Using Help
Installation Guide
Installing from a release
- Download the packagedReleaseVersion.
- Unzip and run AsrTools.exe to launch the GUI interface.
- System requirements: Windows 10 or later.
download from a network drive
Installation from source (developers)
- Clone the repository and go to the project directory:
git clone https://github.com/WEIFENG2333/AsrTools.git cd AsrTools
- Install the dependency and run it:
pip install -r requirements.txt python asr_gui.py
Guidelines for use
- Launching the application: Run the downloaded executable or launch the GUI interface via the command line.
- Select ASR Engine: Select the ASR engine you need to use in the drop-down menu (Cutscene, Racer, Must Cut).
- To add a file: Click the "Select File" button or drag and drop the file/folder to the specified area.
- Start Processing: Click "Start Processing" button, the program will automatically start converting and generate SRT or TXT subtitle files in the original audio directory after completion (3 threads are kept running by default).
Pure code call example
- Install the requests library:
pip install requests
- Use the sample code:
from bk_asr import BcutASR, JianYingASR, KuaiShouASR audio_file = "resources/test.mp3" asr = BcutASR(audio_file) # can choose between BcutASR, JianYingASR, KuaiShouASR. result = asr.run() srt = result.to_srt() # Generate SRT subtitle files txt = result.to_txt() # Generate TXT subtitle files json_data = result.to_json() # Returns a dictionary (with time) print(txt)