Create README.md

README.md

@@ -0,0 +1,106 @@
+---
+license: apache-2.0
+base_model: iic/speech_eres2netv2_sv_zh-cn_16k-common
+tags:
+  - speaker-diarization
+  - speaker-recognition
+  - speaker-embedding
+  - onnx
+  - quantized
+  - int8
+  - sherpa-onnx
+library_name: sherpa-onnx
+---
+
+## `diarize-embedding-eres2netv2-int8.onnx`
+
+Statically int8-quantized [ERes2NetV2](https://arxiv.org/abs/2406.02167) speaker
+embedder (3D-Speaker, `zh-cn 16k-common`), for speaker diarization under
+sherpa-onnx.
+
+- **28 MB** (fp32 source: 71 MB), 192-dim embeddings, 16 kHz.
+- Drop-in for `SpeakerEmbeddingExtractorConfig`: the sherpa `metadata_props`
+  (`framework`, `sample_rate`, `output_dim`, `feature_normalize_type`) are
+  preserved, which the extractor requires.
+
+### Why quantize
+
+fp32 ERes2NetV2 separates close voices well, but its 2D convolutions cost about
+**10x** CAM++'s embedding time — roughly 11 minutes on a 19-minute meeting,
+untenable on the no-GPU laptops this app targets. Static quantization removes
+that objection:
+
+| build | time per 6 s window (ORT CPU, 4 threads) |
+|---|---|
+| fp32 | 223 ms |
+| **int8 static (this file)** | **77 ms — 2.9x faster** |
+| int8 *dynamic* | 528 ms — 2.4x **slower** |
+
+Dynamic quantization is a trap here: it lowers `Conv` to `ConvInteger`, which
+onnxruntime's CPU provider does not optimize. Static quantization lowers to
+`QLinearConv`, which it does.
+
+### Accuracy
+
+Against the fp32 model on real meeting windows: embedding cosine **≥ 0.9956**
+(mean 0.9973), and the pairwise-similarity matrix — what clustering actually
+consumes — drifts by at most **0.019**.
+
+End-to-end on diarization bench (DER against hand-annotated references):
+
+| fixture | CAM++ | this model |
+|---|---|---|
+| 2-speaker interview, 28 min | DER 12.6%, 2 voices | DER 12.7%, 2 voices |
+| 2-speaker phone call, 8 min | DER 14.6%, 2 voices | DER 14.5%, 2 voices |
+| multi-speaker meeting, 19 min | 2 voices, 80/20 speech split | **3 voices, 42/37/21** |
+
+Two-speaker recordings cannot tell these models apart. The difference appears
+where it matters — a meeting with several voices, where CAM++ collapses 80% of
+the speech onto one speaker.
+
+Both models still undercount a crowded room (3 of 5 real speakers on that
+meeting), so lets the user pin the speaker count rather than trust
+auto-detection.
+
+### How it was made
+
+`quantize_static` with `QuantFormat.QOperator`, per-channel int8 weights, uint8
+activations, `Conv` only, calibrated on ~40 log-mel fbank windows (600 frames
+≈ 6 s, per-window global-mean normalized, matching sherpa's own preprocessing)
+taken from a real meeting recording. Model metadata is copied back from the
+fp32 file afterwards, since the quantizer drops it.
+
+The script lives in the app repo (`scripts/quantize-eres2netv2.py`):
+
+```bash
+python3 scripts/quantize-eres2netv2.py \
+    eres2netv2-fp32.onnx diarize-embedding-eres2netv2-int8.onnx \
+    some-real-meeting.mp3
+```
+
+### Verifying this file
+
+```
+sha256  be6b162137d8b08854268a97763c007e49882f221e02950242923d40d2be157e
+```
+
+## Credits and license
+
+The weights derive from
+[`iic/speech_eres2netv2_sv_zh-cn_16k-common`](https://www.modelscope.cn/models/iic/speech_eres2netv2_sv_zh-cn_16k-common)
+by the [3D-Speaker](https://github.com/modelscope/3D-Speaker) team (Apache-2.0);
+the fp32 ONNX export came via
+[csukuangfj/speaker-embedding-models](https://huggingface.co/csukuangfj/speaker-embedding-models).
+This repository redistributes a quantized derivative under the same Apache-2.0
+terms. If you use it, cite the original work:
+
+```bibtex
+@inproceedings{eres2netv2,
+  title     = {{ERes2NetV2}: Boosting Short-Duration Speaker Verification
+               Performance with Computational Efficiency},
+  author    = {Chen, Yafeng and Zheng, Siqi and Wang, Hui and Cheng, Luyao and
+               Zhu, Tinglong and Huang, Rongjie and Qian, Chong and Chen, Qian
+               and Zhang, Wen and Wang, Yanmin},
+  booktitle = {Interspeech},
+  year      = {2024}
+}