PytorchSR
PytorchSR copied to clipboard
Pytorch based phoneme recognition (TIMIT phoneme classification)
Implementation Speech Recognition Papers
Authors
- appleholic ([email protected])
- Occupation KakaoBrain AI Developer, june.one
Implementations
sources
- Completed to code training template.
- TODOS:
- evaluate
- more papers
References
- phoneme classification
- Prenet + CBHG in paper:
- paper: Tacotron: Towards End-to-End Speech Synthesis
- PER : to be reported
- Revising GRU :
- paper: Improving speech recognition by revising gated recurrent units
- Minimal GRU:
- Implemented No Reset Gate GRU
- TODOs:
- Cuda Base Implementation
- reference impl sample link : https://github.com/chrischoy/pytorch-custom-cuda-tutorial
- Recurrent Dropout
- Cuda Base Implementation
Setup and Run
Environment
- python 3.6
- pytorch 0.3.1
- hyperparameters with yaml (in hparams folder)
Setup
$ pip install -r requirements.txt
Command
$ python run.py train --model cbhg
Purposes:
- Study Speech Recognition Systems
- Well define source code structure in using pytorch