CoolFace
Modelpublic

aystream/GigaAM-v3-e2e-rnnt-mlx

sourceHugging Facemitupdated 6mo agoView on Hugging Face
1likes217downloads
Model Card

GigaAM v3 e2e RNNT — MLX

MLX port of GigaAM-v3 RNNT variant for Apple Silicon. Higher quality than CTC, ~77x realtime on M2 Max.

Usage

bash
pip install git+https://github.com/aystream/gigaam-mlx.git
python
from gigaam_mlx import load_model, transcribe

model, tokenizer = load_model("rnnt")  # downloads automatically
text = transcribe(model, tokenizer, "recording.wav")

Or via CLI:

bash
gigaam-mlx recording.wav --model-type rnnt

CTC vs RNNT

VariantSpeed (20s chunk)QualityFull 18-min video
CTC0.06s (~330x)Good21.5s
RNNT (this)0.26s (~77x)Better25.0s

Links