You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

saga-2

Danish speech recognition.

Inference

pip install -r requirements.txt
python run.py clip.wav                       # weights from this directory
python run.py --repo capacit-ai/saga-2-m a.wav b.mp3   # or fetch from the hub
python run.py --json out.jsonl *.flac

from saga2 import load
m = load("capacit-ai/saga-2-m")   # cuda if available, else cpu
print(m.transcribe("clip.wav"))
print(m.transcribe(["a.wav", "b.wav"], batch_size=8))

Any sample rate or container librosa can read. Audio over 30 s is split at silences into pieces of at most 28 s and joined.

Downloads last month: -

Safetensors

Model size

1B params

Tensor type

BF16