metadata
license: apache-2.0
language:
- zh
- en
base_model:
- MediaTek-Research/Breeze-ASR-25
- openai/whisper-large-v2
tags:
- audio
- automatic-speech-recognition
library_name: ctranslate2
Breeze ASR 25 model for CTranslate2
This repository contains the conversion of MediaTek-Research/Breeze-ASR-25 to the CTranslate2 model format.
This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper.
Example
from faster_whisper import WhisperModel
model = WhisperModel("phate334/Breeze-ASR-25-ct2")
segments, info = model.transcribe("audio.mp3")
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 /data/models/MediaTek-Research-Breeze-ASR-25/ --output_dir /data/models/Breeze-ASR-25-ct2 --copy_files tokenizer.json preprocessor_config.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.