Speech Recognition for Uyghur using deep learning
| cafe.wav | ||
| data.py | ||
| perlin.wav | ||
| radionoise.wav | ||
| README.md | ||
| silence.wav | ||
| test1.wav | ||
| test2.wav | ||
| test3.wav | ||
| test4.wav | ||
| test5.wav | ||
| test6.wav | ||
| thuyg20_test.csv | ||
| thuyg20_train.csv | ||
| tonu.py | ||
| train.py | ||
| UModel.py | ||
| uyghur.py | ||
| white.wav | ||
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/)