| ---
|
| 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 models
|
|
|
| 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
|
|
|
| ### 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 |
|
|
|
| ### 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 |
|
|
|
| ### Russian summarization (Default tier — NER-based, no LLM)
|
|
|
| | 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 |
|
|
|
| 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.
|
|
|
| ### Manifest
|
|
|
| | 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:
|
| - 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.
|
|
|
| ## How the app uses these models
|
|
|
| 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
|
|
|
| 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
|
|
|
| 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
|
|
|
| ```python
|
| import hashlib
|
|
|
| with open("gigaam_v3_e2e_ctc_int8.onnx", "rb") as f:
|
| print(hashlib.sha256(f.read()).hexdigest())
|
| # expected: 0aacb41f70f0f5aaac4b45dd430337b9e16b180f22c72af04db8516e7609c3c0
|
| ```
|
|
|
| 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 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.
|
|
|
