#!/usr/bin/env bash
CUDA_VISIBLE_DEVICES=0 python run_speech_recognition_seq2seq.py \
        --dataset_name="hf-internal-testing/librispeech_asr_dummy" \
        --model_name_or_path="openai/whisper-tiny.en" \
        --dataset_config_name="clean" \
        --train_split_name="validation" \
        --eval_split_name="validation" \
        --output_dir="./" \
        --preprocessing_num_workers="1" \
        --length_column_name="input_length" \
        --overwrite_output_dir \
        --num_train_epochs="1" \
        --per_device_train_batch_size="8" \
        --per_device_eval_batch_size="8" \
        --learning_rate="3e-4" \
        --warmup_steps="500" \
        --evaluation_strategy="steps" \
        --text_column_name="text" \
        --save_strategy="no" \
        --evaluation_strategy="epoch" \
        --logging_steps="10" \
        --save_total_limit="1" \
        --generation_max_length="40" \
        --generation_num_beams="1" \
        --fp16 \
        --gradient_checkpointing \
        --group_by_length \
        --predict_with_generate \
        --do_train --do_eval \
        --do_lower_case

#!/usr/bin/env bash
CUDA_VISIBLE_DEVICES=0 python run_speech_recognition_seq2seq.py \
    --model_name_or_path="openai/whisper-medium.en" \
    --dataset_name="librispeech_asr" \
    --dataset_config_name="all" \
    --train_split_name="train.clean.100+train.clean.360+train.other.500" \
    --eval_split_name="validation.clean" \
    --max_steps="5000" \
    --output_dir="./" \
    --run_name="whisper-librispeech" \
    --per_device_train_batch_size="64" \
    --per_device_eval_batch_size="16" \
    --logging_steps="25" \
    --learning_rate="1e-4" \
    --warmup_steps="500" \
    --report_to="wandb" \
    --preprocessing_num_workers="16" \
    --evaluation_strategy="steps" \
    --eval_steps="1000" \
    --save_strategy="steps" \
    --save_steps="1000" \
    --generation_max_length="224" \
    --generation_num_beams="1" \
    --length_column_name="input_length" \
    --gradient_checkpointing \
    --group_by_length \
    --freeze_encoder \
    --fp16 \
    --overwrite_output_dir \
    --do_train \
    --do_eval \
    --predict_with_generate \
    --use_auth_token