Faster Whisper Small

🚀 Whisper small model for CTranslate2

This repository provides the conversion of the openai/whisper-small model into the CTranslate2 model format. It enables the use of this model in CTranslate2 and related projects, offering efficient and fast automatic speech recognition capabilities.

🚀 Quick Start

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

💻 Usage Examples

Basic Usage

from faster_whisper import WhisperModel

model = WhisperModel("small")

segments, info = model.transcribe("audio.mp3")
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 openai/whisper-small --output_dir faster-whisper-small \
    --copy_files tokenizer.json --quantization float16

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.