Name		Name	Last commit message	Last commit date
parent directory ..
figs		figs
README.md		README.md
config.yml		config.yml
saved_model.py		saved_model.py
test.py		test.py
tflite.py		tflite.py
train.py		train.py

README.md

Conformer: Convolution-augmented Transformer for Speech Recognition

Reference: https://arxiv.org/abs/2005.08100

Example Model YAML Config

Go to config.yml

Usage

Training, see python examples/conformer/train_*.py --help

Testing, see python examples/conformer/test_*.py --help

TFLite Conversion, see python examples/conformer/tflite_*.py --help

Conformer Subwords - Results on LibriSpeech

Summary

Number of subwords: 1031
Maxium length of a subword: 4
Subwords corpus: all training sets, dev sets and test-clean
Number of parameters: 10,341,639
Positional Encoding Type: sinusoid concatenation
Trained on: 4 RTX 2080Ti 11G

Pretrained and Config, go to drive

Transducer Loss

Error Rates

Test-clean	Test batch size	WER (%)	CER (%)
Greedy	1	6.37933683	2.4757576
Greedy V2	1	7.86670732	2.82563138

Test-other	Test batch size	WER (%)	CER (%)
Greedy	1	15.7308521	7.67273521