Lucky Wong

> Hi, thanks for sharing. Is it normal for a negative loss? It is normal to observe that the loss value is getting smaller and smaller, because the average word...

> i find tf ctc beam search will loss the gradients Beam search is just to find candidate paths, gradient is not required in beam search. Gradients are pushed back...

> Thanks for sharing the codes. Could you provide an example of the o1 loss? I've combined it with the CTC loss as shown in the following code, but it...

> Thanks for your response. > > I have another question regarding CTC optimization. In your experience, what modification in this repository has been most beneficial for reducing CTC loss?...

> Hi @TeaPoly! Thank you for creating this project! > > I've been working with @dscripka on something related to [openWakeWord](https://github.com/dscripka/openWakeWord), and thought it would be helpful to build/upload [speexdsp-ns...