| python run_audio_classification.py \ | |
| --model_name_or_path openai/whisper-tiny \ | |
| --dataset_name sanchit-gandhi/marathi-numbers-test \ | |
| --train_split_name train \ | |
| --eval_split_name train \ | |
| --output_dir whisper-tiny-ft-marathi-numbers \ | |
| --overwrite_output_dir \ | |
| --remove_unused_columns False \ | |
| --label_column_name labels \ | |
| --do_train \ | |
| --do_eval \ | |
| --fp16 \ | |
| --learning_rate 3e-5 \ | |
| --max_length_seconds 3 \ | |
| --attention_mask False \ | |
| --warmup_ratio 0.1 \ | |
| --num_train_epochs 5 \ | |
| --per_device_train_batch_size 8 \ | |
| --gradient_accumulation_steps 1 \ | |
| --per_device_eval_batch_size 8 \ | |
| --dataloader_num_workers 4 \ | |
| --logging_strategy steps \ | |
| --logging_steps 10 \ | |
| --evaluation_strategy epoch \ | |
| --save_strategy epoch \ | |
| --load_best_model_at_end True \ | |
| --metric_for_best_model accuracy \ | |
| --save_total_limit 3 \ | |
| --seed 0 \ | |
| --freeze_feature_encoder False \ | |
| --push_to_hub | |