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:
  • train_u2++_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)
  • encoder_dim 256, output_size 256, head 8, linear_units 2048
  • num_blocks 12, cnn_module_kernel 15, group_size 3
• Decoding info:
  • ctc_weight 0.5, reverse_weight 0.3, average_num 20

test clean

decoding mode	full	18	16
attention decoder	3.65	3.88	3.87
ctc_greedy_search	3.46	3.79	3.77
ctc prefix beam search	3.44	3.75	3.74
attention rescoring	3.17	3.44	3.41

test other

decoding mode	full	18	16
attention decoder	8.51	9.24	9.25
ctc_greedy_search	8.94	10.04	10.06
ctc prefix beam search	8.91	10	10.01
attention rescoring	8.21	9.25	9.25

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}