Downloads · 30 days
8
14% of all-time downloads
voicescribe-gigaam
VoiceScribe/voicescribe-gigaam
voicescribe-gigaam is a automatic speech recognition model from VoiceScribe. Use it when you need speech turned into text. It is set up for openvino. The card lists the license as mit.
OpenVINO IR port of ai-sage/GigaAM-v3 revision e2ernnt — Sber's SOTA Russian ASR model (220M parameters, Conformer + RNN-T with end-to-end punctuation and capitalization).
All-time downloads
57
Public
Repo size
446 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin446 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- openvino
- License
- mit
- Model type
- gigaam
- Access
- Public
- Created
- Apr 23, 2026
- Updated
- Apr 23, 2026
- SHA
- 4ebe3341
Base models
Model card
From the Hugging Face model README
GigaAM-v3 e2e_rnnt (OpenVINO IR, pre-converted)
OpenVINO IR port of ai-sage/GigaAM-v3 revision e2e_rnnt — Sber's SOTA Russian ASR model (220M parameters, Conformer + RNN-T with end-to-end punctuation and capitalization).
Conversion done with:
from transformers import AutoModel
import torch
model = AutoModel.from_pretrained("ai-sage/GigaAM-v3", revision="e2e_rnnt", trust_remote_code=True)
model.to_onnx(dir_path="onnx", dtype=torch.float16)
# then:
import openvino as ov
for f in ["encoder", "decoder", "joint"]:
m = ov.convert_model(f"onnx/v3_e2e_rnnt_{f}.onnx")
ov.save_model(m, f"v3_e2e_rnnt_{f}.xml")
Files
| File | Purpose | Size |
|---|---|---|
v3_e2e_rnnt_encoder.xml/.bin | Conformer encoder (main cost) | ~425 MB FP16 |
v3_e2e_rnnt_decoder.xml/.bin | RNN-T decoder (prediction network) | ~2 MB |
v3_e2e_rnnt_joint.xml/.bin | Joint network | ~1.3 MB |
tokenizer.model | SentencePiece vocabulary (1024 subwords) | 250 KB |
config.json | Original model config (for reference) | 2 KB |
Device compatibility (Intel hardware)
Verified on Intel Core Ultra 9 285H (OpenVINO 2025.4.1):
| Device | Encoder | Decoder | Joint | Usable? |
|---|---|---|---|---|
| CPU | ✅ | ✅ | ✅ | Yes (~34× RTFx on 10 s chunk) |
| GPU.0 (Arc Xe2 iGPU) | ✅ | ✅ | ✅ | Yes (~520× RTFx on encoder alone) |
| NPU | ❌ (dynamic shapes) | ✅ | ❌ (dynamic shapes) | Partial only |
Recommended device: Intel Arc iGPU (GPU.0) — fastest and does not compete with NVIDIA for VRAM.
NPU fails compile on encoder/joint due to dynamic input shapes in the exported ONNX (upper bounds 9223372036854775807). A re-export with static reshape at 10 s chunks would likely unlock NPU.
Usage (Python, pure OpenVINO)
import openvino as ov
core = ov.Core()
encoder = core.compile_model("v3_e2e_rnnt_encoder.xml", "GPU.0")
decoder = core.compile_model("v3_e2e_rnnt_decoder.xml", "GPU.0")
joint = core.compile_model("v3_e2e_rnnt_joint.xml", "GPU.0")
# Preprocess: audio 16 kHz mono -> log-mel (64 bins, 20 ms win, 10 ms hop)
# Encoder: features -> encoder outputs
# Decoder + Joint: RNN-T greedy decode loop -> token IDs
# SentencePieceProcessor(tokenizer.model).decode(ids) -> text
A reference Python backend is available in the Voice Scribe project (MIT license).
Credits
- Original model: Sber / ai-sage/GigaAM-v3 (MIT)
- OpenVINO conversion: Voice Scribe project
License
MIT (matches upstream ai-sage/GigaAM-v3).
- Task
- Automatic Speech Recognition
- Library
- openvino
- Type
- gigaam
- License
- mit
- Languages
- ru
- Created
- Apr 23, 2026
- Updated
- Apr 23, 2026