Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,89 @@
+---
+language:
+- fa
+license: cc-by-4.0
+library_name: nemo
+pipeline_tag: automatic-speech-recognition
+tags:
+- automatic-speech-recognition
+- fastconformer
+- persian
+- fa
+- streaming
+- cache-aware
+- on-device
+- webgpu
+- rnnt
+base_model: nvidia/stt_en_fastconformer_hybrid_medium_streaming_80ms
+metrics:
+- wer
+- cer
+---
+
+# Shenava-Rizeh 0.9 — Persian Cache-Aware Streaming ASR (32M)
+
+A tiny (**32M-param**) **cache-aware, multi-latency streaming** Persian (Farsi) ASR model — FastConformer-Hybrid (RNNT + CTC), 16 kHz. Built for **fully offline, on-device, real-time** captioning (WebGPU / WASM / NeMo), part of the [VisualEars](https://huggingface.co/Reza2kn) project (SLT 2026).
+
+**One model serves the entire latency–accuracy curve** (0 / 80 / 480 / 1040 ms) — pick your operating point at inference time, no re-training. Its larger sibling is [`Shenava-Koochik-0.9`](https://huggingface.co/Reza2kn/Shenava-Koochik-0.9) (114M).
+
+## 📊 Results — Golden6669 (held-out gold Persian eval)
+
+Evaluated on [`Reza2kn/visualears-golden-6669`](https://huggingface.co/datasets/Reza2kn/visualears-golden-6669) (6,669 clips, official Persian normalizer), RNNT head:
+
+| `att_context_size` | **Latency** | **WER** | **CER** | WER_bf |
+|---|---|---|---|---|
+| `[70, 0]` | **0 ms** (real-time) | **11.08%** | **3.17%** | 9.68% |
+| `[70, 1]` | 80 ms | 10.85% | 3.08% | 9.43% |
+| `[70, 6]` | 480 ms | 10.56% | 2.93% | 9.14% |
+| `[70, 13]` | 1040 ms | **10.46%** | **2.89%** | 9.03% |
+
+**The curve is nearly flat — only 0.62 pp WER from 0 → 1040 ms.** You get near-best accuracy at **zero lookahead**: a 32M model doing **11.08% WER / 3.17% CER at true real-time**, fully on-device. For reference, the previous-generation single-latency `fa32M` scored 17.40% (and could not run below its trained latency).
+
+### Flatness holds per-condition
+
+The latency penalty is uniform across acoustic conditions — low-latency does **not** fray on the hard far-field/obstructed tail (Golden6669 is deliberately ~94% non-clean):
+
+| Condition | n | 0 ms WER | 1040 ms WER | Δ |
+|---|---|---|---|---|
+| clean | 400 | 13.38 | 12.62 | +0.76 |
+| obstructed | 4,335 | 10.87 | 10.20 | +0.67 |
+| far-field | 1,934 | 11.24 | 10.77 | **+0.47** |
+
+Far-field has the *smallest* 0→1040 ms gap. (`clean` scores worst here — a quirk of Golden6669's small 400-clip clean slice, not a streaming effect.)
+
+`WER_bf` = boundary-forgiven WER (utterances perfect modulo Persian word-spacing conventions counted correct).
+
+## How it was trained
+
+- **Base:** `nvidia/stt_en_fastconformer_hybrid_medium_streaming_80ms` (English cache-aware streaming), persianized by swapping in a Persian **BPE-1024** tokenizer and reinitializing the decoder + joint (encoder kept).
+- **Multi-latency:** `att_context_size = [[70,13],[70,6],[70,1],[70,0]]` (chunked_limited) — one checkpoint covers 0 / 80 / 480 / 1040 ms.
+- **Phase A:** ~7,386 h / 3.66M clips of cleaned, teacher-pseudo-labeled Persian ([`Reza2kn/visualears-persian-pseudo-asr`](https://huggingface.co/datasets/Reza2kn/visualears-persian-pseudo-asr)).
+- **Phase B:** gold-anchor fine-tune on 355 human-verified gold + active-learning corrections.
+- Trajectory: random-init decoder **→ Phase A 17.94% → Phase B 10.46%** (@1040 ms).
+
+## Usage (NeMo)
+
+```python
+from nemo.collections.asr.models import ASRModel
+m = ASRModel.restore_from("shenava-rizeh-0.9.nemo").cuda().eval()
+m.encoder.set_default_att_context_size([70, 0])      # 0 ms (real-time); or [70,13] for best WER
+print(m.transcribe(["clip.wav"])[0].text)
+```
+
+`[70,0]`=0 ms · `[70,1]`=80 ms · `[70,6]`=480 ms · `[70,13]`=1040 ms (1 encoder frame = 80 ms, FastConformer subsampling 8).
+
+## Notes
+- **Version 0.9** — Phase B on 355 human-verified gold. **v1.0** follows a larger active-learning gold round (the 6K worst-disagreement clips now under review on Argilla).
+- The CTC head is the deployment head for real-time/WebGPU; RNNT is the higher-accuracy offline/rescorer head.
+- Larger streaming sibling: [`Shenava-Koochik-0.9`](https://huggingface.co/Reza2kn/Shenava-Koochik-0.9) (114M). Offline flagship: [`shenava-fa-fastconformer-115m`](https://huggingface.co/Reza2kn/shenava-fa-fastconformer-115m) (7.29%).
+
+## Citation
+```bibtex
+@misc{shenava_rizeh_2026,
+  title  = {Shenava-Rizeh: Persian Cache-Aware Streaming ASR (32M)},
+  author = {Sayar, Reza},
+  year   = {2026},
+  howpublished = {Hugging Face},
+  url    = {https://huggingface.co/Reza2kn/Shenava-Rizeh-0.9}
+}
+```