louiskirsch / speechT

An opensource speech-to-text software written in tensorflow
Apache License 2.0
157 stars 36 forks source link

Fixing the sample rate broke pre-trained weights and performance #15

Open louiskirsch opened 7 years ago

louiskirsch commented 7 years ago

After the fixing the sample rate in https://github.com/timediv/speechT/commit/db61338161adee693603e12eb8ac57c66ec80adb the pretrained weights are no longer valid.

After retraining I can not reproduce the same results I obtained previously. I can not look into this issue right now, but will do so soon. For now I'll revert the last commit.