| | |
|---|
| | | |
|---|
| | | ## option 1, download model automatically |
|---|
| | | model_name_or_model_dir="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" |
|---|
| | | model_revision="v2.0.7" |
|---|
| | | |
|---|
| | | ## option 2, download model by git |
|---|
| | | #local_path_root=${workspace}/modelscope_models |
|---|
| | |
|---|
| | | --nproc_per_node ${gpu_num} \ |
|---|
| | | ../../../funasr/bin/train.py \ |
|---|
| | | ++model="${model_name_or_model_dir}" \ |
|---|
| | | ++model_revision="${model_revision}" \ |
|---|
| | | ++train_data_set_list="${train_data}" \ |
|---|
| | | ++valid_data_set_list="${val_data}" \ |
|---|
| | | ++dataset_conf.batch_size=20000 \ |
|---|
| | |
|---|
| | | ++train_conf.resume=false \ |
|---|
| | | ++train_conf.validate_interval=2000 \ |
|---|
| | | ++train_conf.save_checkpoint_interval=2000 \ |
|---|
| | | ++train_conf.avg_keep_nbest_models_type='loss' \ |
|---|
| | | ++train_conf.keep_nbest_models=20 \ |
|---|
| | | ++optim_conf.lr=0.0002 \ |
|---|
| | | ++output_dir="${output_dir}" &> ${log_file} |
|---|
