-
Looking over some BLSTM training logs, I see that the per-element scales w_fc, w_ic and w_oc seem to be learning extremely slowly, never changing much from their initial values. It looks to me like a…
-
Hi, Thanks again for a great program
I tried to run allosaurus on approximately a 15 minute TED talk and got the following error. From the same talk, I extracted a 5 second speech excerpt, and allo…
-
Hello. I trained hn-sinc-nsf model by running project/hn-sinc-nsf-9/00_demo.sh and each generated WAV listed in test_list in config.py sounds good. But when I synthesized a longer WAV, the quality of…
-
Hi @IsaacChanghau,
Thanks for your great work.
I have an issue when running inference. I restore the checkpoint and predict tag for the input sentence. But the error occurs. Can you help me?
```Inf…
-
When I use espnet/egs/mini_an4/asr1/conf/train_transducer.yaml or espnet/egs/vivos/asr1/conf/tuning/transducer/train_transducer.yaml config to train a RNN-T model, I meet a strange problem:
If ng…
-
Hello,
I use the very last version of kaldi,
in teldium/s5_r2 for the python version of train.sh ( train_dnn.py, train_rnn.py ) I notice that the output related to the progress of the GPU traini…
-
**Describe the bug**
I am training tacotron TTS with GST and using token_type=char I got this crash
**Basic environments:**
- OS information: Linux 936c828f17cb 4.15.0-106-generic #107~16.04.1-U…
gafsd updated
4 years ago
-
Hi,
I've been trying to build hybrid models on raw input signals. The raw input signals are sampled with a sampling length of 25ms * 16000Hz = 400 frame width.
These are the two config files I'…
-
Hi!
If I run model on GPU, it's cause
`RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_addmm`
Do you have plans to add cuda suppor…
-
```python
def blstm_layer(self, embedding_chars):
"""
:return:
"""
with tf.variable_scope('rnn_layer'):
cell_fw, cell_bw = self._bi_dir_rnn()
…