Faster Distil Whisper Large V3

🚀 Whisper distil-large-v3 model for CTranslate2

This project provides the conversion of the distil-whisper/distil-large-v3 model to the CTranslate2 format, enabling efficient use in related projects.

🚀 Quick Start

This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper.

✨ Features

• Compatibility: Works well with CTranslate2 and CTranslate2-based projects.
• Efficient Conversion: The original model is converted to CTranslate2 format for better performance.

💻 Usage Examples

Basic Usage

from faster_whisper import WhisperModel

model = WhisperModel("distil-large-v3")

segments, info = model.transcribe("audio.mp3", language="en", condition_on_previous_text=False)
for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

🔧 Technical Details

Conversion details

The original model was converted with the following command:

ct2-transformers-converter --model distil-whisper/distil-large-v3 --output_dir faster-distil-whisper-large-v3 \
    --copy_files tokenizer.json preprocessor_config.json --quantization float16

⚠️ Important Note

Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the compute_type option in CTranslate2.

📚 Documentation

For more information about the original model, see its model card.

📄 License

This project is licensed under the MIT license.