In Mxnet, there are fewer kinds of data iterator for speech research filed.
Could anyone contribute a frame level data iterator for speech recognition?
To my best knowledge, frame level training is more common for speech field.
Related Topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Organizing diverse input data for mxnet models | 0 | 456 | April 3, 2018 | |
|
Multi-label classification using mxnet
|
1 | 2276 | June 29, 2018 | |
| MXNET and Named entity recognition? | 0 | 326 | August 4, 2022 | |
|
MemoryError in Mxnet speech example
|
1 | 516 | September 19, 2018 | |
| MXNet and sparse attention | 0 | 1622 | February 7, 2020 |