accelerate launch --mixed_precision=bf16 run_distillation.py \ | |
--model_name_or_path "./distil-large-v3-init" \ | |
--teacher_model_name_or_path "openai/whisper-large-v3" \ | |
--train_dataset_name "mozilla-foundation/common_voice_15_0" \ | |
--train_dataset_config_name "de" \ | |
--train_split_name "train" \ | |
--text_column_name "sentence" \ | |
--eval_dataset_name "mozilla-foundation/common_voice_15_0" \ | |
--eval_dataset_config_name "de" \ | |
--eval_split_name "validation" \ | |
--eval_text_column_name "sentence" \ | |
--eval_steps 5000 \ | |
--save_steps 5000 \ | |
--warmup_steps 500 \ | |
--learning_rate 1e-4 \ | |
--lr_scheduler_type "linear" \ | |
--logging_steps 25 \ | |
--save_total_limit 1 \ | |
--max_steps 50000 \ | |
--per_device_train_batch_size 64 \ | |
--per_device_eval_batch_size 64 \ | |
--dataloader_num_workers 16 \ | |
--preprocessing_num_workers 16 \ | |
--ddp_timeout 7200 \ | |
--dtype "bfloat16" \ | |
--output_dir "./" \ | |
--use_pseudo_labels "false" \ | |
--wandb_project "huggingface" \ | |
--condition_on_prev_probability "0.0" \ | |
--do_train \ | |
--do_eval \ | |
--gradient_checkpointing \ | |
--overwrite_output_dir \ | |
--predict_with_generate \ | |
--freeze_encoder \ | |
--streaming | |