-
We have tried the following sequence of commands to get the MBR decode using Kaldi offline(not the Kaldi fork from alphacep).
Method 1:
```
lattice-to-ctm-conf --inv-acoustic-scale=12 --decode-…
-
Thanks for your work. In the paper, you mentioned that the teacher model is wavLM + ECAPA-TDNN. However, in your implementation, I only found you loaded the weights of wavLM (line 13 in train/experime…
gancx updated
5 months ago
-
Hi there,
The ECAPA-TDNN model checkpoints on Baidu seem to be inaccessible to non-Chinese users due to the Chinese mobile number requirement for account creation. Could you host them on a more acc…
-
**i use multi_cn/s5/run.sh train model, in the last step local/chain/run_cnn_tdnn.sh , find below bug:**
```
run.pl: job failed, log is in exp/chain_cleaned/tdnn_cnn_1a_sp/log/train.1.3.log
2022-…
-
Hi, i want to finetune my dataset, in stage 4 of run_cvte_ft.sh :
steps/nnet3/chain/get_egs.sh: no such file exp/chain/tdnn_ft/0.trans_mdl
how can i handel it.
-
First, Thanks for the work by babysor!
I noticed that the speaker encoder used in this work is ge2e, performance of which is far fall behind the SOTA. So I replaced the ge2e encoder with ECAPA-TDNN m…
-
![error_report](https://user-images.githubusercontent.com/82881944/146217800-4bd8aa59-f085-4731-8d5c-15907f725ce9.png)
I was testing out the framework on Ed Sheeran's Perfect as an example as a san…
-
First, Thanks for the excellent work by CorentinJ!
I noticed that the speaker encoder used in this work is ge2e, performance of which is far fall behind the SOTA. So I replaced the ge2e encoder with …
-
Hi, I am using MFA for force alignment between phonenes and audio, I want to know nnet3 or chain model is used to train MFA from scarch? As I know than tdnn in nnet3 is better for alignment.
-
Hello authors! I see that in your paper “FASTAUDIO: A LEARNABLE AUDIO FRONT-END FOR SPOOF SPEECH DETECTION”, the input is the CQT feature, the model is ECAPA-TDNN, and the best result obtained is 1.73…