breeze-asr-26

Converted faster-whisper / CTranslate2 model for OpenAI Whisper.

Source (PyTorch): MediaTek-Research/Breeze-ASR-26
Converted artifact: rhap-llm-audio/faster-Breeze-ASR-26
Quantization: float32 (see CTranslate2 quantization)
Device tested: cpu
Converted at: 2026-08-22
Pipeline: whisper-to-faster-whisper

Usage

faster-whisper (Python)

from faster_whisper import WhisperModel

model = WhisperModel(
    "rhap-llm-audio/faster-Breeze-ASR-26",
    device="cpu",
    compute_type="float32",
)
segments, info = model.transcribe("audio.mp3")
for seg in segments:
    print(f"[{seg.start:.2f} → {seg.end:.2f}] {seg.text}")

speaches (OpenAI-compatible STT server)

This model card includes the metadata block speaches filters on (library_name: ctranslate2, pipeline_tag: automatic-speech-recognition, language:). After a regular POST /v1/models download, speaches will list this in GET /v1/models.

curl -X POST http://localhost:8000/v1/models \
  -H 'Content-Type: application/json' \
  -d '{"model": "rhap-llm-audio/faster-Breeze-ASR-26"}'

curl http://localhost:8000/v1/audio/transcriptions \
  -F "file=@audio.mp3" \
  -F "model=rhap-llm-audio/faster-Breeze-ASR-26"

Files

File	Purpose
`model.bin`	CTranslate2 weights (float32)
`config.json`	faster-whisper model config
`vocabulary.json`	tokenizer vocab
`tokenizer.json`	HF tokenizer
`preprocessor_config.json`	whisper feature-extractor config
`README.md`	this card (speaches filter requires it)

License

Inherited from upstream MediaTek-Research/Breeze-ASR-26. See source repo for the original model license. The conversion process itself adds no additional licensing terms.

Downloads last month: 28