whisper-tiny-it-ct2-int8

CTranslate2 INT8 quantized version of LocalAI-io/whisper-tiny-it for fast CPU inference.

Author: Ettore Di Giacinto

Brought to you by the LocalAI team. This model can be used directly with LocalAI.

Model Details

• Base model: openai/whisper-tiny, fine-tuned on Common Voice 25.0 Italian
• Quantization: INT8 via CTranslate2
• Size: 39MB (vs 578MB for the original fp32 model)
• WER: 27.1% on Common Voice 25.0 Italian test set

Usage

faster-whisper

from faster_whisper import WhisperModel

model = WhisperModel("LocalAI-io/whisper-tiny-it-ct2-int8", device="cpu", compute_type="int8")
segments, info = model.transcribe("audio.mp3", language="it")
for segment in segments:
    print(f"[{segment.start:.1f}s - {segment.end:.1f}s] {segment.text}")

WhisperX

import whisperx

model = whisperx.load_model("LocalAI-io/whisper-tiny-it-ct2-int8", device="cpu", compute_type="int8")
result = model.transcribe("audio.mp3", language="it")

LocalAI

This model is compatible with LocalAI for local, self-hosted AI inference.

Links

• HF Safetensors version: LocalAI-io/whisper-tiny-it
• Code: github.com/localai-org/whisper-it
• LocalAI: github.com/mudler/LocalAI