Shenava β€” Rizeh Pizeh v1.0 (6.9M) Β· CTC Streaming Β· ONNX (INT8)

Rizeh Pizeh (Ψ±ΫŒΨ²Ω‡ ΩΎΫŒΨ²Ω‡, "tiny grain") is the 6.9M tiniest student of the Shenava‑1 family β€” capable of real-time inference on a 2015 Cortex-A7. This repository contains the CTC streaming INT8 quantized ONNX export for use with sherpa-onnx.

Model Details

Property Value
Parent Model Reza2kn/Shenava-Rizeh-Pizeh-v1.0
Model Type EncDecCTCModelBPE (pure CTC β€” no transducer head)
Architecture FastConformer Pure CTC
Language Persian (Farsi)
Parameters 6.9M
Vocabulary Size 1025 tokens (BPE + blank)
Tokenizer ve_tok_v4 β€” SentencePiece BPE‑1024
Sample Rate 16 kHz
Subsampling 8Γ—
Streaming βœ… Yes (with cache support)
Weight Type INT8 (dynamic quantization)
Author Reza2kn
Version 1.0

Files

.
β”œβ”€β”€ README.md
β”œβ”€β”€ model.int8.onnx   # ONNX model (INT8 quantized)
└── tokens.txt        # Token vocabulary (1025 tokens)

Usage

sherpa-onnx-offline \
  --tokens=tokens.txt \
  --encoder=model.int8.onnx \
  --num-threads=4 \
  /path/to/test.wav

Conversion

Exported from a NeMo checkpoint and quantized dynamically with ONNX Runtime.

License

CC-BY-NC 4.0 (inherited from the parent model)

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for mah92/sherpa-onnx-nemo-ctc-fa-shenava-rizeh-pizeh-v1.0-streaming-int8-2026-06-26

Datasets used to train mah92/sherpa-onnx-nemo-ctc-fa-shenava-rizeh-pizeh-v1.0-streaming-int8-2026-06-26