Open source, https://github.com/albertz/
The same also for the LSTM paper after you click on 'cite'.
The same also for the LSTM paper after you click on 'cite'.
For the grad ctc_loss w.r.t. log_probs, it calculates exp(log_probs) - y, but correct would be -y. Some workaround: github.com/pytorch/pyto...
PS: First Bluesky post.
For the grad ctc_loss w.r.t. log_probs, it calculates exp(log_probs) - y, but correct would be -y. Some workaround: github.com/pytorch/pyto...
PS: First Bluesky post.