Kotoba Whisper V2.2 Faster

🚀 Whisper kotoba-whisper-v2.2 Model for CTranslate2

This project provides the conversion of the kotoba-tech/kotoba-whisper-v2.2 model to the CTranslate2 format, enabling its use in CTranslate2 and related projects.

🚀 Quick Start

📦 Installation

First, install the necessary library and obtain a sample audio file.

pip install faster-whisper

💻 Usage Examples

Basic Usage

Perform inference using the kotoba-whisper-v2.2-faster model.

from faster_whisper import WhisperModel

if __name__ == '__main__':
    model = WhisperModel(model_size_or_path="./kotoba-whisper-v2.2-faster", device="cuda", compute_type="float32", local_files_only=True)
    segments, info = model.transcribe(audio="./123.wav", language="ja", chunk_length=5, condition_on_previous_text=False, hotwords="ノイミー")

    for segment in segments:
        print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

🔧 Technical Details

Conversion Details

The original model was converted using the following command:

ct2-transformers-converter --model kotoba-tech/kotoba-whisper-v2.2 --output_dir kotoba-whisper-v2.2-faster --copy_files tokenizer.json preprocessor_config.json --quantization float32

Note that the model weights are saved in FP32 format. You can change this type when loading the model using the compute_type option in CTranslate2.

📚 Documentation

For more information about the kotoba-whisper-v2.2 model, refer to the original model card.

📄 License

This project is licensed under the MIT License.