Shenava-Rizeh-Pizeh-v1.0

🐣🎙️ Shenava Rizeh-Pizeh v1.0 · شنوا ریزه‌پیزه

The smallest Shenava-1 Persian ASR model: a 6.9M-parameter FastConformer distilled through the Koochik → Rizeh → Rizeh-Pizeh cascade. This repository contains the FP32 NeMo source checkpoint for evaluation, fine-tuning, and export.

✨ At a glance | معرفی سریع

• Canonical repository: Reza2kn/Shenava-Rizeh-Pizeh-v1.0
• PersianML mirror: PersianML/Shenava-Rizeh-Pizeh-v1.0
• Teacher: Reza2kn/Shenava-Rizeh-v1.0

🧠 Model contract

• Audio: mono, 16 kHz Persian speech.
• Encoder: d_model=144, 12 layers, 8x subsampling.
• Contexts: [70,13], [70,6], [70,1], and [70,0].
• Deployed head: CTC.
• Tokenizer: ve_tok_v4, SentencePiece BPE-1024 plus blank.
• Output: Persian text; use display-layer ITN when Persian digits are required.

The release reported real-time FP32 tract inference on a 2015 Cortex-A7 (RTF about 0.91). Treat that as a release-specific device measurement, not a universal latency guarantee.

📊 Published evaluation

Decoded with context [70,13] and the double-benchmark ITN/Persian-digit normalization convention.

🚀 Load with NeMo

from nemo.collections.asr.models import ASRModel

model = ASRModel.restore_from("shenava-rizeh-pizeh-v1.0.nemo")
print(model.transcribe(["speech.wav"])[0].text)

Choose this model when footprint and low-end CPU viability matter more than the accuracy available from the 32M Rizeh or 114M Koochik checkpoints.

🇮🇷 خلاصهٔ فارسی

«شنوا ریزه‌پیزه» کوچک‌ترین مدل خانواده است: ۶٫۹ میلیون پارامتر برای اجرای کم‌هزینه روی CPUهای ضعیف. این مخزن checkpoint اصلی FP32 و NeMo را نگه می‌دارد؛ اندازهٔ کم با افت دقت نسبت به ریزه و کوچیک همراه است.

🌌 Explore Shenava-1

🧠 Koochik 114M · ⚖️ Rizeh 32M · 🐣 Rizeh-Pizeh 6.9M

Apache-2.0. Accuracy varies with accent, noise, overlap, recording channel, and code-switching.