-
请问在最后结合BERT模型的实验中，由于BERT_Tokenizer会把序列切分为字序列，是如何将lexicon中匹配的词输入到BERT中的？
-
This is fairly easy to do: in the current MMI script, just add a scaling factor on the denominator likelood, like 0.9 or 0.8 or something.
-
I was trying to use this recipe to train an ASR model with the CGN corpus, but I'm getting an empty segments error in the `cgn_data_prep.sh` when I run the `run.sh` script.
I changed the CGN root t…
-
-
Hi, I finished the training of TDNN-LSTM-CTC，when I run the step of decoding, I met a error:
2021-09-28 14:56:23,027 INFO [decode.py:349] Decoding started
2021-09-28 14:56:23,048 INFO [decode.py:3…
cdxie updated
7 months ago
-
Hey there!
Can we port ztachip to the following FPGAs with less than 100,000 LUTs:
1. Digilent Cmod A7-35T: Artix-7 with 35,000 LUTs
2. Cmod A7-15T: Artix-7 FPGA Module with 15,000 LUTs
3. CrossLi…
-
`WARNING:absl:Found untraced functions such as lstm_cell_2_layer_call_fn, lstm_cell_2_layer_call_and_return_conditional_losses, lstm_cell_2_layer_call_fn, lstm_cell_2_layer_call_and_return_conditional…
-
First, thanks a lot for your amazing job, it is so helpful!
**Describe the bug**
I tried to convert a pretrained model of PointPillars (Kitti 3class) to tensorrt but the conversion failed. To be…
-
Running speech synthesis ONNX models on an ARM embedded platform without a GPU, using only the CPU？
-
I followed you installation instructions and receive the following error messages:
```R
pak::pak(sprintf("rstudio/%s", c("reticulate", "tensorflow", "keras")))
! Using bundled GitHub PAT. Please …