Whisper-Large-v3 Arabic (Fine-Tuned Standalone FP16)

Fine-tuned Whisper-Large-v3 on Modern Standard Arabic and regional Arabic speech, achieving 12.51% Word Error Rate (WER) on Mozilla Common Voice 17.0 test set.

• High-throughput inference: For 18.0x realtime deployment with low memory, see the INT8 quantized version: Omar10lfc/whisper-large-v3-arabic-ct2-int8.

Arabic Speech Recognition Benchmark (Common Voice 17.0)

All models were evaluated on the canonical Mozilla Common Voice 17.0 Arabic test set using the standardized normalization protocol:

Model Details

• Base Architecture: openai/whisper-large-v3 (1,550M parameters, 32 encoder layers, 32 decoder layers)
• Training Method: Parameter-Efficient QLoRA ($r=64$, $\alpha=128$, targeted q_proj, v_proj) fused into standalone FP16 weights.
• Language: Arabic (ar)
• Primary Task: Speech-to-Text Transcription

FP16 (Unquantized) vs. CTranslate2 INT8 Quantization Comparison

Does 8-bit quantization degrade accuracy? Our empirical benchmark across the full Mozilla Common Voice Arabic evaluation suite demonstrates quantization parity—the Word Error Rate (WER) difference between unquantized FP16 and CTranslate2 Static INT8 is statistically negligible ($\le 0.5$ to $0.8$ percentage points), while reducing disk size and VRAM by ~50% and accelerating inference by up to $3.6\times$:

Production Recommendations

• Deploy CTranslate2 INT8 (*-ct2-int8): Recommended for production APIs, serverless containers (Modal, RunPod, Hugging Face Spaces), and edge environments to cut cold-start load times and memory by half while maximizing throughput.
• Deploy PyTorch FP16: Recommended for further domain fine-tuning, research workflows, or systems requiring native Hugging Face transformers pipeline integration.

Quickstart (Transformers)

import torch
from transformers import AutoModelForConditionalGeneration, AutoProcessor, pipeline

model_id = "Omar10lfc/whisper-large-v3-arabic"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    device_map="cuda"
)

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    generate_kwargs={"language": "arabic", "task": "transcribe"}
)

result = pipe("path/to/arabic_audio.mp3")
print("Transcription:", result["text"])