58AILab/wenet_efficient_conformer_librispeech_v1

Efficient Conformer v1 for non-streaming ASR

Specification: https://github.com/wenet-e2e/wenet/pull/1636

Results

• —Feature info:
• —using fbank feature, cmvn, speed perturb, dither
• —Training info:
• —trainu2++efficonformer_v1.yaml
• —8 gpu, batch size 16, acc_grad 1, 120 epochs
• —lr 0.001, warmup_steps 35000
• —Model info:
• —Model Params: 49,474,974
• —Downsample rate: 1/4 (conv2d) * 1/2 (efficonformer block)
• —encoderdim 256, outputsize 256, head 8, linear_units 2048
• —numblocks 12, cnnmodulekernel 15, groupsize 3
• —Decoding info:
• —ctcweight 0.5, reverseweight 0.3, average_num 20

test clean

test other

Start to Use

Install WeNet follow: https://wenet.org.cn/wenet/install.html#install-for-training

Decode

cd examples/librispeech/s0

cp exp/wenet_efficient_conformer_librispeech_v1/decode.sh ./
cp exp/wenet_efficient_conformer_librispeech_v1/wer.sh ./

dir=exp/wenet_efficient_conformer_librispeech_v1
decoding_chunk_size=-1
. ./decode.sh ${dir} 20 ${decoding_chunk_size}

# WER
. ./wer.sh test_clean wenet_efficient_conformer_librispeech_v1 ${decoding_chunk_size}
. ./wer.sh test_other wenet_efficient_conformer_librispeech_v1 ${decoding_chunk_size}