Powered by π€ Transformers & Optimum and based on Vaibhavs10/insanely-fast-whisper.
TL;DR - ποΈ Transcribe 300 minutes (5 hours) of audio in less than 10 minutes - with OpenAI's Whisper Large v2. Blazingly fast transcription is now a reality!β‘οΈ
β¨ ASR Model: Choose from different π€ Hugging Face ASR models, including all sizes of openai/whisper and even use an English-only variant (for non-large models).
π Performance: Customizable optimizations ASR processing with options for batch size, data type, and BetterTransformer, all from the comfort of your terminal! π
π Timestamps: Get an SRT output file with accurate timestamps, allowing you to create subtitles for your audio or video content.
git clone https://github.com/ochen1/insanely-fast-whisper-cli
cd insanely-fast-whisper-cli/
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python insanely-fast-whisper.py
insanely-fast-whisper --model openai/whisper-base --device cuda:0 --dtype float32 --batch-size 8 --better-transformer --chunk-length 30 your_audio_file.wav
model
: Specify the ASR model (default is "openai/whisper-base").device
: Choose the computation device (default is "cuda:0").dtype
: Set the data type for computation ("float32" or "float16").batch-size
: Adjust the batch size for processing (default is 8).better-transformer
: Use BetterTransformer for improved processing (flag).chunk-length
: Define audio chunk length in seconds (default is 30).Transcribing an audio file with English-only Whisper model and returning timestamps:
insanely-fast-whisper --model openai/whisper-base.en your_audio_file.wav
The tool will save an SRT transcription of your audio file in the current working directory.
This project is licensed under the MIT License.
Have questions or feedback? Feel free to create an issue!
π Star this repository if you find it helpful!
π Happy transcribing with Insanely Fast Whisper! π