Downloads · 30 days
136
27% of all-time downloads
GigaAM-v3-e2e-ctc-mlx
aystream/GigaAM-v3-e2e-ctc-mlx
GigaAM-v3-e2e-ctc-mlx is a automatic speech recognition model from aystream. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as mit.
MLX port of GigaAM-v3 for fast Russian speech recognition on Apple Silicon. 180x realtime on M2 Max.
All-time downloads
496
Public
Repo size
884 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors884 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- mit
- Model type
- gigaam
- Access
- Public
- Created
- Mar 24, 2026
- Updated
- Mar 24, 2026
- SHA
- e9c03f41
Base models
Model card
From the Hugging Face model README
GigaAM v3 e2e CTC — MLX
MLX port of GigaAM-v3 for fast Russian speech recognition on Apple Silicon. 180x realtime on M2 Max.
Usage
pip install gigaam-mlx
from gigaam_mlx import load_model, transcribe
model, tokenizer = load_model() # downloads weights automatically
text = transcribe(model, tokenizer, "recording.wav")
print(text)
Or via CLI:
gigaam-mlx recording.wav
Performance
MacBook Pro M2 Max, 20-second chunk:
| Backend | Time | Realtime |
|---|---|---|
| MLX CTC (this) | 0.11s | 180x |
| PyTorch MPS RNNT | 0.76s | 26x |
| ONNX CPU CTC | 1.66s | 12x |
Model
- Architecture: Conformer (16 layers, 768d, 16 heads, RoPE) + CTC
- Parameters: 220M
- Vocabulary: 257 tokens (SentencePiece)
- Features: Punctuation, text normalization, Russian + English code-switching
Links
- Code: github.com/aystream/gigaam-mlx
- Original: salute-developers/GigaAM (paper)
- License: MIT
- Task
- Automatic Speech Recognition
- Library
- mlx
- Type
- gigaam
- License
- mit
- Languages
- ru, en
- Created
- Mar 24, 2026
- Updated
- Mar 24, 2026