Downloads · 30 days
0
Shenava-Koochik-v1.0-tract-streaming
Reza2kn/Shenava-Koochik-v1.0-tract-streaming
Shenava-Koochik-v1.0-tract-streaming is a automatic speech recognition model from Reza2kn. Use it when you need speech turned into text. It is set up for onnx. The card lists the license as apache-2.0.
Cache-aware Persian CTC streaming for the pure-Rust tract runtime. This bundle does not require ONNX Runtime or a C++ inference library.
Access
Public
Updated Aug 11, 2026
Repo size
771 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx771 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- onnx
- License
- apache-2.0
- Access
- Public
- Created
- Jul 3, 2026
- Updated
- Aug 11, 2026
- SHA
- 3c957761
Base models
Model card
From the Hugging Face model README
🦀🌊🎙️ Shenava Koochik v1.0 — tract streaming
Cache-aware Persian CTC streaming for the pure-Rust tract runtime. This bundle does not require ONNX Runtime or a C++ inference library.
✨ At a glance | معرفی سریع
| English | فارسی | |
|---|---|---|
| 🦀 Runtime | Pure Rust with tract | اجرای خالص Rust با tract |
| 🌊 Mode | True cache-aware streaming | اجرای جریانی واقعی با cache |
| 🪶 Smallest graph | 138 MB INT4 | کوچک‌ترین گراف INT4 با حجم ۱۳۸MB |
| 🎧 Input | 121-frame log-mel chunks | chunkهای ۱۲۱ فریمی log-mel |
| 🔌 Dependencies | No ONNX Runtime or C++ engine | بدون ONNX Runtime یا موتور C++ |
- Canonical repository:
Reza2kn/Shenava-Koochik-v1.0-tract-streaming - PersianML mirror:
PersianML/Shenava-Koochik-v1.0-tract-streaming - Parent:
Reza2kn/Shenava-Koochik-v1.0
📦 Pick a graph
| File | Precision | Size | Intended use |
|---|---|---|---|
model.int4.onnx | Q4_0 weight-only | 138 MB | Recommended edge/streaming graph. |
model.int8.onnx | dynamic INT8 matmul | 174 MB | Useful where INT8 kernels win; can be slower for batch-1 streaming. |
model.onnx | FP32 | 459 MB | Reference graph. |
The release’s parity checks reported byte-identical greedy transcripts for INT4 and INT8 versus FP32. The published x86 measurement for FP32 was about 83.9 ms per 1.12-second chunk (RTF about 0.075); treat this as release-specific, not a promise for other hardware.
🌊 Streaming contract
audio_signal: FP32[1, 80, 121], unnormalized NeMo log-mel.length: INT64[1], the true valid frame count.cache_last_channel:[1, 17, 70, 512].cache_last_time:[1, 17, 512, 8].cache_last_channel_len: INT64[1].- Output: CTC log-probabilities plus the next cache tensors.
Feed 121-frame chunks with a shift of 112 frames and 9 frames of pre-encode overlap. Pad the first and final chunks, but pass their true lengths. Initialize cache tensors to zero, thread the returned caches into the next step, and preserve the previous CTC token across chunk boundaries when collapsing repeats. Blank id is 1024; map tokens with tokens.txt and convert SentencePiece ▁ to spaces.
🧩 tract compatibility
NeMo FastConformer cache-aware graph support was merged into tract main in sonos/tract#2441. Use a tract revision containing that change. shenava_tract_streaming.patch remains in this repository for older tract revisions and reproducibility.
persian_itn.py optionally converts spoken Persian numbers to Persian digits.
🇮🇷 خلاصهٔ فارسی
این مخزن مدل جریانی cache-aware برای موتور خالص Rust یعنی tract است. برای دستگاه‌های edge فایل INT4 پیشنهاد می‌شود. cacheها را از هر مرحله به مرحلهٔ بعد منتقل کنید و هنگام CTC collapse توکن قبلی را بین chunkها حفظ کنید.
🌌 Explore Shenava-1
🧠 Koochik source · 🦀 tract streaming · 📼 tract offline · 🌐 Browser ONNX · 🍎 Core ML
Apache-2.0.
- Task
- Automatic Speech Recognition
- Library
- onnx
- License
- apache-2.0
- Languages
- fa
- Created
- Jul 3, 2026
- Updated
- Aug 11, 2026