aishell example

游雁

2024-02-19 6a9c21a40882dc59676dc882954b290e0a867960

 examples/industrial_data_pretraining/paraformer/finetune.sh

@@ -6,10 +6,12 @@
#git clone https://www.modelscope.cn/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}

## generate jsonl from wav.scp and text.txt
#python funasr/datasets/audio_datasets/scp2jsonl.py \
#++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
#++data_type_list='["source", "target"]' \
#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl
python funasr/datasets/audio_datasets/scp2jsonl.py \
++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl


# torchrun \
# --nnodes 1 \
# --nproc_per_node 1 \