File size: 754 Bytes
4748e7c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 |
python run_flax_speech_recognition_seq2seq.py \
--model_name_or_path="openai/whisper-small" \
--dataset_name="mozilla-foundation/common_voice_13_0" \
--dataset_config_name="hi" \
--language="hindi" \
--train_split_name="train+validation" \
--eval_split_name="test" \
--output_dir="./" \
--per_device_train_batch_size="16" \
--per_device_eval_batch_size="16" \
--num_train_epochs="10" \
--learning_rate="1e-4" \
--warmup_steps="500" \
--logging_steps="25" \
--generation_max_length="40" \
--preprocessing_num_workers="32" \
--dataloader_num_workers="32" \
--max_duration_in_seconds="30" \
--text_column_name="sentence" \
--overwrite_output_dir \
--do_train \
--do_eval \
--predict_with_generate \
--push_to_hub \
--use_auth_token
|