Home|About|Gaming cabinet|Archives|How it works|Starter sites

GeezerVison is showing github.com — GitHub - ftian1/CaffeDeepSpeech2: The caffe implementation of DeepSpeech2

Open more actions menu

Latest commit

History

4 Commits

Folders and files

Name		Name	Last commit message	Last commit date
ctc		ctc
data		data
LICENSE		LICENSE
README.md		README.md
audio_data_loader.py		audio_data_loader.py
ds2_cont_filler_layer.py		ds2_cont_filler_layer.py
ds2_ctc_loss_layer.py		ds2_ctc_loss_layer.py
ds2_data_layer.py		ds2_data_layer.py
solver.prototxt		solver.prototxt
train.prototxt		train.prototxt

Repository files navigation

CaffeDeepSpeech2

The caffe implementation of DeepSpeech2

It's a minimal version of caffe deep speech2. I dropped out many bn1d layers as caffe doesn't support it yet.

TODO LIST:

variable length support -- depends on caffe implementation
batch normal 1d support -- same as above
bidirection support -- same as above
gru support -- same as above

About

The caffe implementation of DeepSpeech2

Resources

Apache-2.0 license

Stars

0 stars

Watchers

2 watching

Forks

Report repository

Releases

Packages

Contributors

Languages