Update README: document English ASR and Russian summarization models

README.md

@@ -2,75 +2,111 @@
 license: apache-2.0
 language:
   - ru
+  - en
 tags:
   - automatic-speech-recognition
   - speaker-diarization
+  - named-entity-recognition
+  - text-summarization
   - onnx
   - russian
+  - english
   - asr
   - gigaam
+  - whisper
   - 3d-speaker
   - camplus
   - eres2net
+  - slovnet
+  - natasha
+  - navec
   - mobile
   - offline
 library_name: onnx
 ---
 
-# ProtocolVoice ASR Models
+# ProtocolVoice models
 
-ONNX models for offline Russian speech recognition and speaker diarization,
-packaged for the [ProtocolVoice](https://github.com/protocolvoice) Android app.
+Offline models for the [ProtocolVoice](https://github.com/conwerter1/protocolvoice) Android app — voice transcription, speaker diarization, and on-device interview summarization.
+
+All models run **on the device**, no cloud calls.
 
 ## Contents
 
-| File | Size | Purpose | Original source | Original license |
+### Russian ASR
+
+| File | Size | Purpose | Original source | License |
 |---|---|---|---|---|
 | `gigaam_v3_e2e_ctc_int8.onnx` | 305 MB | Russian ASR with built-in punctuation | [Sber/SaluteDevices GigaAM](https://github.com/salute-developers/GigaAM) (v3, e2e CTC, int8-quantized) | MIT |
-| `speaker_embedding_camplus.onnx` | 27 MB | Speaker embedding (CAM++) | [modelscope/3D-Speaker](https://github.com/modelscope/3D-Speaker) | Apache-2.0 |
-| `speaker_embedding.onnx` | 111 MB | Speaker embedding (ERes2Net) | [modelscope/3D-Speaker](https://github.com/modelscope/3D-Speaker) | Apache-2.0 |
+
+### English ASR
+
+| File | Size | Purpose | Original source | License |
+|---|---|---|---|---|
+| `en/whisper_base_en_encoder_int8.onnx` | 28 MB | Whisper base.en encoder | [openai/whisper](https://github.com/openai/whisper) via [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) | MIT |
+| `en/whisper_base_en_decoder_int8.onnx` | 125 MB | Whisper base.en decoder | OpenAI Whisper via sherpa-onnx | MIT |
+| `en/whisper_base_en_tokens.txt` | 0.8 MB | Whisper tokens vocab | OpenAI Whisper | MIT |
+
+### Speaker diarization (works for any language)
+
+| File | Size | Purpose | Original source | License |
+|---|---|---|---|---|
+| `speaker_embedding_camplus.onnx` | 27 MB | Speaker embedding (CAM++) — recommended default | [modelscope/3D-Speaker](https://github.com/modelscope/3D-Speaker) | Apache-2.0 |
+| `speaker_embedding.onnx` | 111 MB | Speaker embedding (ERes2Net V1) — best quality | [modelscope/3D-Speaker](https://github.com/modelscope/3D-Speaker) | Apache-2.0 |
 | `speaker_embedding_v2.onnx` | 68 MB | Speaker embedding (ERes2NetV2) | [modelscope/3D-Speaker](https://github.com/modelscope/3D-Speaker) | Apache-2.0 |
-| `manifest.json` | < 1 KB | SHA-256 hashes of all models | this repo | Apache-2.0 |
 
-## Important
+### Russian summarization (Default tier — NER-based, no LLM)
 
-These are NOT new models — this repository **redistributes existing models** in ONNX
-format for convenient mobile delivery. The original authors retain all credit and
-copyright. We did not train, fine-tune, or modify the model weights.
+| File | Size | Purpose | Original source | License |
+|---|---|---|---|---|
+| `summary/navec_news.tar` | 25 MB | Navec quantized word embeddings (250K Russian words, 300-dim, PQ-100) | [natasha/navec](https://github.com/natasha/navec) | MIT |
+| `summary/slovnet_ner.tar` | 2.3 MB | Slovnet NER weights (WordCNN + CRF, PER/LOC/ORG) | [natasha/slovnet](https://github.com/natasha/slovnet) | MIT |
 
-**Please cite the original projects, not this redistribution:**
+These two files together (28 MB total) enable offline Russian named entity recognition + LexRank-based extractive summarization. ProtocolVoice uses them to extract names, organizations, locations, and key quotes from interview transcripts. No LLM required — fully deterministic, factual extraction.
 
-- **GigaAM-v3** (ASR): Sber AI, SaluteDevices —
-  https://github.com/salute-developers/GigaAM
-- **3D-Speaker** (CAM++, ERes2Net, ERes2NetV2): ModelScope, Alibaba —
-  https://github.com/modelscope/3D-Speaker
+### Manifest
 
-The ONNX conversions and runtime were prepared via [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx)
-(Apache-2.0).
+| File | Size | Purpose |
+|---|---|---|
+| `manifest.json` | < 2 KB | SHA-256 hashes and metadata for all models |
+
+## Important — attribution
+
+These are NOT new models — this repository **redistributes existing models** in formats convenient for mobile delivery. The original authors retain all credit and copyright. We did not train, fine-tune, or modify the model weights.
+
+**Please cite the original projects, not this redistribution:**
+
+- **GigaAM-v3** (Russian ASR): Sber AI, SaluteDevices — https://github.com/salute-developers/GigaAM
+- **Whisper** (English ASR): OpenAI — https://github.com/openai/whisper
+- **3D-Speaker** (CAM++, ERes2Net, ERes2NetV2): ModelScope, Alibaba — https://github.com/modelscope/3D-Speaker
+- **Slovnet NER + Navec**: Natasha project, Alexander Kukushkin — https://github.com/natasha/slovnet, https://github.com/natasha/navec
+- **sherpa-onnx** (ONNX runtime): Next-gen Kaldi (k2-fsa) — https://github.com/k2-fsa/sherpa-onnx
 
 ## Why this redistribution
 
-The ProtocolVoice mobile app needs to download these models on first run from a
-mirror that:
+The ProtocolVoice mobile app needs to download these models on first run from a mirror that:
 - supports files larger than 100 MB without git-lfs limits,
 - has fast CDN reachable from Russia,
 - is the conventional hosting platform for ML models.
 
-All redistributed files retain their original licenses. This README serves as
-the required attribution under those licenses.
+All redistributed files retain their original licenses. This README serves as the required attribution under those licenses.
 
-## How to use
+## How the app uses these models
 
-Each model is loaded by [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) on
-the device. The ProtocolVoice app:
+ASR + diarization (loaded via [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx)):
+1. App downloads `.onnx` files from `https://huggingface.co/protocolvoice/asr-models/resolve/main/{filename}`
+2. Verifies SHA-256 against `manifest.json`
+3. Loads via sherpa-onnx for offline inference
 
-1. Downloads each `.onnx` file by HTTP from
-   `https://huggingface.co/protocolvoice/asr-models/resolve/main/{filename}`,
-2. Verifies SHA-256 against `manifest.json`,
-3. Loads via sherpa-onnx for offline inference.
+Summarization (Default tier, custom Kotlin port):
+1. App downloads `summary/navec_news.tar` and `summary/slovnet_ner.tar`
+2. Extracts both `.tar` archives into the app's private files directory
+3. Loads weights into a pure-Kotlin reimplementation of Slovnet NER (no PyTorch, no Python — just FloatArray math): WordEmbedding → ShapeEmbedding → 3-layer Conv1D → Linear → CRF Viterbi
+4. Combines NER output with TF-IDF + LexRank to extract top quotes, named entities, risks, and numerical data
 
-You can also use these files directly with sherpa-onnx in any project that
-respects the original licenses.
+Inference performance on Xiaomi 12T: ~6 seconds for a 17,900-word transcript (default tier, NER + LexRank, no LLM).
+
+You can also use these files directly with the upstream libraries (sherpa-onnx, slovnet, navec) in any project that respects the original licenses.
 
 ## Verifying integrity
 
@@ -84,16 +120,16 @@ with open("gigaam_v3_e2e_ctc_int8.onnx", "rb") as f:
 
 Hashes for all files are in `manifest.json`.
 
+## Optional: Pro tier (QVikhr 1.5B)
+
+ProtocolVoice has an optional **PRO tier** that produces a literary, narrative summary using [QVikhr-2.5-1.5B-Instruct-r](https://huggingface.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r) (1.0 GB GGUF, runs via llama.cpp on-device). The PRO tier is layered on top of the Default tier — Default extracts facts, PRO turns them into a coherent narrative.
+
+The QVikhr GGUF is **not hosted in this repo** — users download it directly from the Vikhrmodels HF org or from a separate mirror, on demand. The QVikhr authors retain copyright; please cite them, not us.
+
 ## License
 
-This repository's metadata, README, and packaging scripts are released under
-**Apache-2.0**. Each model file remains under its original license (see the
-table above). By using a model, you accept its original license — not just
-this repository's.
+This repository's metadata, README, and packaging scripts are released under **Apache-2.0**. Each model file remains under its original license (see the tables above). By using a model, you accept its original license — not just this repository's.
 
 ## Removal request
 
-If you are an author of one of the upstream projects and have any concerns
-about this redistribution (attribution, hosting, anything else), please open
-a discussion on this Hugging Face repo or email the maintainers — the files
-will be amended or removed as requested.
+If you are an author of one of the upstream projects and have any concerns about this redistribution (attribution, hosting, anything else), please open a discussion on this Hugging Face repo or email the maintainers — the files will be amended or removed as requested.