English
tinymyo
emg
bio-signals
foundation-model

Fine-tuned Gaddy EMG-to-text checkpoint / recipe for the 33.95% WER result?

#1
by erdenebayrd - opened

Hi Matteo, thank you for releasing TinyMyo and the silent_speech code.

I'm a student at MIT (Melbourne Institute of Technology in Australia) reproducing your EMG-to-text (recognition) results on the Gaddy
dataset as a baseline for some research. I've reproduced the from-scratch 4-layer setting
(~40.8% test WER, beam 1500) and I'm now fine-tuning from
pretraining/TinyMyo/TinyMyo.safetensors (8 layers) to reach the paper's ~33.95%.

Two questions, either would help a lot:

  1. Could you share the fine-tuned recognition checkpoint on Gaddy (the .pt that
    start_training_from expects, i.e. the ~33.95% WER model)? I'd use it directly as a baseline.
  2. If not, could you confirm the fine-tuning recipe: num_epochs / early-stopping patience,
    LR schedule and peak LR, whether freeze_blocks was used, and the SizeAwareSampler token budget?

I've verified the backbone's transformer blocks load into the fork's EMGTransformer.
Thanks very much!
Erdenebayar Dovchindorj (MIT)

Sign up or log in to comment