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

aystream/GigaAM-v3-e2e-ctc-mlx

GigaAM v3 e2e CTC — MLX

Usage

Performance

Model

Links

aystream/
GigaAM-v3-e2e-ctc-mlx