15 lines
457 B
Markdown
15 lines
457 B
Markdown
# Speech Recognition for Uyghur using deep learning
|
|
Training:
|
|
|
|
this model using CTC loss for training.
|
|
|
|
Download pretrained model and dataset from https://github.com/gheyret/uyghur-asr-ctc/releases.
|
|
unzip results.7z and thuyg20_data.7z to the same folder where python source files located. then run:
|
|
|
|
python train.py
|
|
|
|
|
|
This project using
|
|
|
|
A free Uyghur speech database Released by CSLT@Tsinghua University & Xinjiang University(http://www.openslr.org/22/)
|