whisper-large-v3-turbo-it-multi-yodas-asr_only-nocv-ct2-int8

CTranslate2 INT8 quantization of LocalAI-io/whisper-large-v3-turbo-it-multi-yodas-asr_only-nocv for fast CPU/GPU inference via faster-whisper / WhisperX / LocalAI.

Usage

from faster_whisper import WhisperModel
model = WhisperModel("LocalAI-io/whisper-large-v3-turbo-it-multi-yodas-asr_only-nocv-ct2-int8", device="cpu", compute_type="int8")
segments, _ = model.transcribe("audio.mp3", language="it")
for s in segments:
    print(f"[{s.start:.1f}s] {s.text}")

Brought to you by the LocalAI team.