Skip to content

Releases: RF5/simple-speech-commands

Add pretrained resnext sc09 model

04 May 12:52
@RF5 RF5
Compare
Choose a tag to compare

This includes the pretrained model adapted from https://github.com/HazyResearch/state-spaces/tree/main/sashimi/sc09_classifier . Please see details in original repo for model training specification. Its usage is the same as existing models, however gradient flow from waveform to output is not supported due to reliance on librosa mel-spectrogram transform.

v0.6 SC09 Model Release

20 Apr 11:00
@RF5 RF5
Compare
Choose a tag to compare

Add convgru_classifier_sc09 checkpoint file. Include checkpoint both from end (3k steps), or from lowest validation loss (ckpt_lowest_validation).

Initial model release

05 Mar 10:11
@RF5 RF5
Compare
Choose a tag to compare

Add convgru classifier checkpoint.