| CUDA_VISIBLE_DEVICES=1 python run_speech_recognition_seq2seq.py \ | |
| --dataset_name="librispeech_asr" \ | |
| --model_name_or_path="./" \ | |
| --dataset_config_name="clean" \ | |
| --train_split_name="train.100" \ | |
| --eval_split_name="validation" \ | |
| --output_dir="./" \ | |
| --preprocessing_num_workers="1" \ | |
| --length_column_name="input_length" \ | |
| --overwrite_output_dir \ | |
| --num_train_epochs="3" \ | |
| --per_device_train_batch_size="8" \ | |
| --per_device_eval_batch_size="8" \ | |
| --gradient_accumulation_steps="2" \ | |
| --generation_max_length="40" \ | |
| --generation_num_beams="1" \ | |
| --learning_rate="3e-4" \ | |
| --warmup_steps="500" \ | |
| --evaluation_strategy="steps" \ | |
| --text_column_name="text" \ | |
| --save_steps="500" \ | |
| --eval_steps="500" \ | |
| --logging_steps="1" \ | |
| --save_total_limit="1" \ | |
| --freeze_feature_encoder \ | |
| --gradient_checkpointing \ | |
| --fp16 \ | |
| --group_by_length \ | |
| --predict_with_generate \ | |
| --do_lower_case \ | |
| --do_eval --do_train \ | |
| --push_to_hub \ | |
| --use_auth_token | |