---
language:
- ckb
pipeline_tag: automatic-speech-recognition
library_name: pytorch
tags:
- icefall
- zipformer2
- streaming
- rnnt
- sorani
---

# Sorani Zipformer2 · Streaming ASR

**Central Kurdish speech → text, running locally on your CPU.**

Run B is a causal Zipformer2 trained from scratch on **188.70 hours** of human,
pseudo-labeled, and synthetic speech. This release contains **one checkpoint**:
the development-selected running-model average spanning **epochs 17–24**.

**66.14M parameters · 512-piece BPE · 320 ms chunks · 2.56 s left context**

## Quick start

Use Python 3.12 and a fresh environment:

```bash
python3.12 -m venv .venv
source .venv/bin/activate
pip install --upgrade pip huggingface_hub
hf download Amin-khattab/sorani-zipformer2-streaming --local-dir sorani-model
pip install -r sorani-model/requirements.txt
python sorani-model/transcribe.py recording.wav
```

Add `--partials` to display changing text as chunks are processed. WAV and FLAC
are recommended; the script converts to mono and resamples to 16 kHz.
The verified runtime is **Mac CPU**. Other platforms have not been tested.

## Use in your application

From the downloaded `sorani-model` directory:

```python
import numpy as np
from transcribe import Recognizer

model = Recognizer(".")                 # load once
stream = model.create_stream()          # new stream per utterance

# Replace silence with mono float32 microphone PCM at 16 kHz, in [-1, 1].
pcm = np.zeros(5120, dtype=np.float32)   # 320 ms packet
print(stream.accept(pcm))               # repeat for each incoming packet
print(stream.accept(np.empty(0, dtype=np.float32), final=True))
```

Each stream retains its encoder/decoder state. `final=True` flushes the last
words using 500 ms of silence. Resample microphone input before feeding it;
convert int16 PCM to float32 and divide by 32768.

**Format:** TorchScript (`torch.jit.load`), not a Transformers `pipeline()` model.
The script provides **greedy decoding**; microphone capture and a hosted API are
not included. Output is Sorani text without punctuation restoration.

## Test results

**2,014 held-out utterances · 3.014328 hours · cached streaming greedy decoding**

| Model | WER ↓ | CER ↓ |
|---|---:|---:|
| Run A · Common Voice only | 41.24% | 12.14% |
| **Run B · this release** | **23.69%** | **4.54%** |

**42.55% relative WER reduction** over Run A. Both models used the same test set
and decoder. WER uses whitespace-separated words; CER uses Unicode codepoints
excluding whitespace. Scores use corpus edit totals without text normalization.

Development results were **21.40% WER / 4.13% CER**, using four-path modified beam
search. Those are separate development scores, not test results. Selection used
development data only. Audio hashes and utterance IDs were checked for split
overlap; speaker-disjointness is not established because speaker metadata was unavailable.

## Training & limitations

30 epochs · 20,938 updates · RTX 3060 12 GB · FP16 · ScaledAdam + Eden.
SpecAugment enabled; MUSAN/noise mixing and speed perturbation disabled.
The tokenizer was trained only on Common Voice training transcripts.

Accuracy on other languages, noise, code-switching, and uncommon names is not
established. No diarization, timestamps, or automatic endpointing is included.
Chunk size is not measured latency: formal RTF and first-partial/finalization
latencies remain unbenchmarked. Verify important transcriptions manually.

[Technical details](TECHNICAL_DETAILS.md) cover data proportions, architecture,
averaging, feature settings, and runtime differences. [evaluation.json](evaluation.json)
contains the aggregate scores; [SHA256SUMS](SHA256SUMS) verifies the release files.

**License:** a reuse license for these weights has not yet been specified.
Contact [Amin Khattab](https://huggingface.co/Amin-khattab) for licensing; public
access does not grant unrestricted reuse. Built with
[Icefall / Zipformer2](https://github.com/k2-fsa/icefall), whose upstream code is Apache-2.0 licensed.