>
O
Model Details
Introduction
S1-mini: WER (Word Error Rate): 0.011 CER (Character Error Rate): 0.005 Distance: 0.380
Training
Training Code AccessibilityCC-BY-NC-SA-4.0 https://huggingface.co/fishaudio/openaudio-s1-mini Here is a codebase for their previous model (Fish-Speech, Apache License) but not his one https://github.com/fishaudio/fish-speech/tree/main/fish_speech
Parameters
Parameters500000000
Notes: S1-mini (0.5B): A distilled version of S1.
