ja__Ivydata__whisper-small-japanese__int8

CTranslate2 export of Whisper Small for ja (usable with faster-whisper).

Usage

from faster_whisper import WhisperModel
model = WhisperModel("ja__Ivydata__whisper-small-japanese__int8", device="cpu", compute_type="int8")  # or cuda / int8_float16
segments, info = model.transcribe("sample.wav", language="ja")
for s in segments:
    print(f"[{s.start:.2f} -> {s.end:.2f}] {s.text}")

Tip: If you get a language mismatch, pass language="<code>" explicitly.