Whisper CLI is a powerful tool for audio transcription and translation directly from your terminal. Whether you’re working with podcasts, interviews, or conference recordings, Whisper CLI makes it easy to convert spoken content into text in various languages. In this guide, we’ll walk you through installing Whisper CLI, using it for different purposes, and explore its language options, use cases, and potential areas for expansion.
Table of Contents
Introduction to Whisper CLI
Whisper CLI by OpenAI is an automatic speech recognition (ASR) system that excels in audio transcription and translation tasks. This tool supports over 60 languages and provides accurate text conversion from spoken audio. Whisper CLI is ideal for content creators, developers, and businesses looking for a reliable and efficient transcription solution.
For more information about Whisper CLI, check the official GitHub repository.
Installing Whisper CLI
Prerequisites:
- Python 3.7 or higher
pip(Python package installer)
Step-by-Step Installation:
Install Python and pip:
For Linux/macOS, use:
$ sudo apt update && sudo apt install python3 python3-pipFor macOS, you can also use Homebrew:
$ brew install python3Install Whisper CLI: Install Whisper CLI directly from its GitHub repository using pip:
$ pip3 install git+https://github.com/openai/whisper.gitOptional: Install PyTorch: Whisper CLI relies on PyTorch for neural network computations. Install PyTorch for optimized performance:
$ pip3 install torch torchvision torchaudioVerify Installation: After installation, verify it by running:bashCopy codewhisper --help
Basic Usage of Whisper CLI
With Whisper CLI installed, you can start transcribing and translating audio files with simple commands.
Transcribing Audio Files:
To transcribe an audio file to text, use:
$ whisper path/to/audio.mp3 --task transcribeTranslating Audio Files to English:
Whisper CLI can translate audio from any supported language into English:
$ whisper path/to/audio.mp3 --task translateSpecify Output Format:
To output transcription in different formats, such as .srt:
$ whisper path/to/audio.mp3 --output_format srtSpecify Output Directory:
To save the output in a specific directory:
$ whisper path/to/audio.mp3 --output_dir /path/to/output_directoryFor detailed usage, refer to the Whisper CLI documentation.
Language Options in Whisper CLI
Whisper CLI supports over 60 languages for transcription and translation. Here’s a complete list of supported languages:
To specify a language manually, use:
whisper path/to/audio.mp3 --language [language_code] --task transcribeLanguage Options Table
| Code | Language |
|---|---|
| af | Afrikaans |
| am | Amharic |
| ar | Arabic |
| as | Assamese |
| az | Azerbaijani |
| ba | Bashkir |
| be | Belarusian |
| bg | Bulgarian |
| bn | Bengali |
| bo | Tibetan |
| bs | Bosnian |
| ca | Catalan |
| cs | Czech |
| cy | Welsh |
| da | Danish |
| de | German |
| el | Greek |
| en | English |
| es | Spanish |
| et | Estonian |
| eu | Basque |
| fa | Persian |
| fi | Finnish |
| fr | French |
| gl | Galician |
| gu | Gujarati |
| he | Hebrew |
| hi | Hindi |
| hr | Croatian |
| ht | Haitian Creole |
| hu | Hungarian |
| hy | Armenian |
| id | Indonesian |
| is | Icelandic |
| it | Italian |
| ja | Japanese |
| jv | Javanese |
| ka | Georgian |
| kk | Kazakh |
| km | Khmer |
| kn | Kannada |
| ko | Korean |
| ku | Kurdish |
| ky | Kyrgyz |
| la | Latin |
| lb | Luxembourgish |
| lo | Lao |
| lt | Lithuanian |
| lv | Latvian |
| mg | Malagasy |
| mi | Maori |
| mk | Macedonian |
| ml | Malayalam |
| mn | Mongolian |
| mr | Marathi |
| ms | Malay |
| mt | Maltese |
| my | Burmese |
| ne | Nepali |
| nl | Dutch |
| no | Norwegian |
| or | Oriya |
| pa | Punjabi |
| pl | Polish |
| ps | Pashto |
| pt | Portuguese |
| ro | Romanian |
| ru | Russian |
| sa | Sanskrit |
| sd | Sindhi |
| si | Sinhala |
| sk | Slovak |
| sl | Slovenian |
| sq | Albanian |
| sr | Serbian |
| su | Sundanese |
| sv | Swedish |
| sw | Swahili |
| ta | Tamil |
| te | Telugu |
| th | Thai |
| tl | Tagalog |
| tr | Turkish |
| tt | Tatar |
| uk | Ukrainian |
| ur | Urdu |
| uz | Uzbek |
| vi | Vietnamese |
| xh | Xhosa |
| yi | Yiddish |
| zh | Chinese (Mandarin) |
| zu | Zulu |
Use Cases for Whisper CLI
Whisper CLI offers a range of applications across various fields:
- Media and Content Creation: Transcribe interviews, podcasts, and generate subtitles.
- Education: Transcribe lectures and aid language learning.
- Business: Generate meeting minutes and improve customer support.
- Legal: Transcribe legal proceedings and documents.
Potential Areas of Expansion
Whisper CLI has potential for future improvements:
- Real-Time Transcription: Implement live transcription for events and calls.
- API Integration: Develop APIs for cloud-based transcription services.
- Language-Specific Models: Enhance accuracy for specific languages.
- Audio File Format Support: Broaden the range of supported audio formats.
- NLP Integration: Combine with NLP tools for advanced text analysis.
Handling NumPy Compatibility Issues
If you encounter an issue where a module compiled with NumPy 1.x cannot run in NumPy 2.0.1, you need to either downgrade NumPy or rebuild the module. Here’s how to do it:
Downgrade NumPy
Uninstall Current NumPy Version:
pip uninstall numpyInstall Compatible NumPy Version:
pip install 'numpy<2'Conclusion
Whisper CLI is a robust tool for audio transcription and translation, providing users with high-quality text conversion from audio files in multiple languages. By following this guide, you can effectively use Whisper CLI for various purposes and explore its full potential.
For more information, visit the Whisper CLI GitHub repository.
