aystream/GigaAM-v3-e2e-ctc-mlx

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:

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