It is optimized for lightning-fast inference and low memory usage using the faster-whisper library. The model was fine-tuned on a mix of Indonesian and English datasets, including Google FLEURS, Common Voice 22.0, and EdAcc (for Indonesian-accented English).

Model Details

Original Model: Dafisns/whisper-turbo-multilingual-fleurs
Base Architecture: OpenAI Whisper Large V3 Turbo
Format: CTranslate2 (INT8 / Float16 quantization)
Optimization: Up to 4x faster inference compared to standard Transformers with significantly reduced VRAM usage.

Performance (WER)

The following Word Error Rates (WER) were achieved by the original model on the combined test sets:

Language	Dataset Composition	WER (%)
English	Fleurs + Common Voice + EdAcc	9.09%
Indonesian	Fleurs + Common Voice	6.97%

Installation

You need to install the faster-whisper library to use this model efficiently:

bash

pip install faster-whisper
from faster_whisper import WhisperModel

# Use 'cuda' for GPU or 'cpu' for CPU
# 'float16' is recommended for GPU, 'int8' for CPU
model_id = "Dafisns/whisper-turbo-multilingual-fleurs-ct2"

model = WhisperModel(model_id, device="cuda", compute_type="float16")

# Transcribe audio file
# Setting language='id' ensures the model focuses on Indonesian
segments, info = model.transcribe("audio.mp3", beam_size=1, language="id")

print(f"Detected language '{info.language}' with probability {info.language_probability}")

for segment in segments:
    print(f"[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}")

Dafisns/whisper-turbo-multilingual-cf-ct2

Whisper Turbo Multilingual (CTranslate2 / Faster-Whisper)

Model Details

Performance (WER)

Installation

Dafisns/
whisper-turbo-multilingual-cf-ct2