protocolvoice/asr-models

ProtocolVoice ASR Models

ONNX models for offline Russian speech recognition and speaker diarization, packaged for the ProtocolVoice Android app.

Contents

File	Size	Purpose	Original source	Original license
gigaam_v3_e2e_ctc_int8.onnx	305 MB	Russian ASR with built-in punctuation	Sber/SaluteDevices GigaAM (v3, e2e CTC, int8-quantized)	MIT
speaker_embedding_camplus.onnx	27 MB	Speaker embedding (CAM++)	modelscope/3D-Speaker	Apache-2.0
speaker_embedding.onnx	111 MB	Speaker embedding (ERes2Net)	modelscope/3D-Speaker	Apache-2.0
speaker_embedding_v2.onnx	68 MB	Speaker embedding (ERes2NetV2)	modelscope/3D-Speaker	Apache-2.0
manifest.json	< 1 KB	SHA-256 hashes of all models	this repo	Apache-2.0

Important

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.

Please cite the original projects, not this redistribution:

• 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

The ONNX conversions and runtime were prepared via sherpa-onnx (Apache-2.0).

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 to use

Each model is loaded by sherpa-onnx on the device. The ProtocolVoice app:

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.

You can also use these files directly with sherpa-onnx in any project that respects the original licenses.

Verifying integrity

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.

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.

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.