SoybeanMilk/faster-whisper-Breeze-ASR-25

Breeze-ASR-25 Model for CTranslate2

This repository contains the MediaTek-Research/Breeze-ASR-25 model converted to the CTranslate2 format.

The model can be used with CTranslate2 or CTranslate2-based projects such as faster-whisper.

Example

from faster_whisper import WhisperModel

model = WhisperModel("SoybeanMilk/faster-whisper-Breeze-ASR-25")

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

Conversion Details

The original model was converted with the following command:

ct2-transformers-converter \
  --model MediaTek-Research/Breeze-ASR-25 \
  --output_dir faster-whisper-Breeze-ASR-25 \
  --copy_files tokenizer.json preprocessor_config.json \
  --quantization float16

Note: The model weights are saved in FP16 format. You can change the type when loading the model using the compute_type option in CTranslate2.

More Information

For more information about the original model, please refer to its model card