|
#!/usr/bin/env bash |
|
|
|
export CUDA_VISIBLE_DEVICES= |
|
|
|
./zipformer/export-onnx-streaming.py \ |
|
--tokens ./icefall-asr-librispeech-streaming-zipformer-2023-05-17/data/lang_bpe_500/tokens.txt \ |
|
--use-averaged-model 0 \ |
|
--epoch 99 \ |
|
--avg 1 \ |
|
--exp-dir ./icefall-asr-librispeech-streaming-zipformer-2023-05-17/exp \ |
|
--num-encoder-layers "2,2,3,4,3,2" \ |
|
--downsampling-factor "1,2,4,8,4,2" \ |
|
--feedforward-dim "512,768,1024,1536,1024,768" \ |
|
--num-heads "4,4,4,8,4,4" \ |
|
--encoder-dim "192,256,384,512,384,256" \ |
|
--query-head-dim 32 \ |
|
--value-head-dim 12 \ |
|
--pos-head-dim 4 \ |
|
--pos-dim 48 \ |
|
--encoder-unmasked-dim "192,192,256,256,256,192" \ |
|
--cnn-module-kernel "31,31,15,15,15,31" \ |
|
--decoder-dim 512 \ |
|
--joiner-dim 512 \ |
|
--causal True \ |
|
--chunk-size 16 \ |
|
--left-context-frames 128 |
|
|