-
Dear all,
I have a trained acoustic model (AM.bin) and a language model(LM.arpa). The training was done on my local machine. So all the train.cfg file had the paths as shown below( here all the loc…
-
Hey guys, I'm seeing another error in a similar flavor to #234 which was resolved by doing a pull from `master`. Unfortunately, since the last time I pulled (April 3rd) there doesn't seem to have been…
-
I'm currently working on streaming decode, but I got stuck when feeding the data with small chunk, it returns very diffrence result compare with full audio decoding.
In [eda528d](https://github.com/f…
-
Hi, I'm trying to build an end-to-end ASR system for Mandarin Chinese using this toolkit. My training looks fine to me as shown below:
```
epoch: 1 | lr: 0.050000 | lrcriterion: 0.050000 | ru…
-
It's not an issue, I just want to ask some questions to make sure all is good. Please let me know if I need to ask this on some other forum.
I am training WSJ using a single Tesla K80 GPU with the …
-
Hi,
I have trained the example dataset and now I would like to use the acoustic model on own wav file to produce as output the mentioned words. Is there any description how I can do this? Do I just…
-
When training for a different language, my understanding is, I need to provide: 1) lexicon, 2) tokens, 3) training dataset, 4) pretrained language model. And when I run train.cpp, it will train only 2…
-
I tried to complete the training with the example training configuration, but when I used the trained model to decode, there are no candidates output.
>[root@dd88309d-124c-4caf-b665-f87d8b1b66d1 /d…
-
I am planning on training / validating / testing with audio files with multiple sentences.
I have a few concerns:
1. when preparing `.tkn` and `.wrd` files, should we put each sentence on separat…
-
Hello, I have trained in THCH30 dataset, train and test stage is OK,but decode failed!
- data details as fellowed:
```
000000000.id : file_id 0
000000000.tkn: 七 十 二 岁 | 的 | 黄 浦 区 | 第 一 | 饮 食 | 公 司…