Chinese-English-mixed ASR model using icefall_conv_emformer2
Wenetspeech testset results
| TEST_NET | TEST_MEETING |
|---|---|
| 9.64 | 9.2 |
as log in decoding_results/modified_beam_search_result
Training commond
python3 conv_emformer_transducer_stateless2/train.py --world-size 8 --num-epochs 30 --start-epoch 1 --exp-dir conv_emformer_transducer_stateless2/exp --max-duration 400 --master-port 12321 --num-encoder-layers 12 --chunk-length 32 --cnn-module-kernel 31 --left-context-length 32 --right-context-length 8 --memory-size 32