| python run_speech_recognition_ctc.py \ | |
| --dataset_name="NbAiLab/NPSC" \ | |
| --model_name_or_path="KBLab/wav2vec2-large-voxrex" \ | |
| --dataset_config_name="16K_mp3" \ | |
| --output_dir="./" \ | |
| --overwrite_output_dir \ | |
| --num_train_epochs="15" \ | |
| --per_device_train_batch_size="16" \ | |
| --per_device_eval_batch_size="16" \ | |
| --gradient_accumulation_steps="2" \ | |
| --learning_rate="1e-4" \ | |
| --warmup_steps="2000" \ | |
| --length_column_name="input_length" \ | |
| --evaluation_strategy="steps" \ | |
| --text_column_name="text" \ | |
| --save_steps="500" \ | |
| --eval_steps="500" \ | |
| --logging_steps="100" \ | |
| --layerdrop="0.041" \ | |
| --attention_dropout="0.094" \ | |
| --activation_dropout="0.055" \ | |
| --hidden_dropout="0.047" \ | |
| --save_total_limit="3" \ | |
| --freeze_feature_encoder \ | |
| --feat_proj_dropout="0.04" \ | |
| --mask_time_prob="0.082" \ | |
| --mask_time_length="10" \ | |
| --mask_feature_prob="0.25" \ | |
| --mask_feature_length="64" \ | |
| --gradient_checkpointing \ | |
| --min_duration_in_seconds="0.5" \ | |
| --max_duration_in_seconds="30.0" \ | |
| --use_auth_token \ | |
| --seed="42" \ | |
| --fp16 \ | |
| --group_by_length \ | |
| --do_train --do_eval \ | |
| --push_to_hub \ | |
| --preprocessing_num_workers="32" | |