File size: 951 Bytes
daf256a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
28
29
30
31
32
#!/usr/bin/env bash
#CUDA_VISIBLE_DEVICES="0" python run_speech_recognition_seq2seq.py \
python -m torch.distributed.launch \
 	--nproc_per_node 8 run_speech_recognition_seq2seq.py \
	--dataset_name="librispeech_asr" \
	--model_name_or_path="./" \
	--dataset_config_name="clean" \
	--train_split_name="train.100" \
	--eval_split_name="validation" \
	--output_dir="./" \
	--preprocessing_num_workers="16" \
	--length_column_name="input_length" \
	--overwrite_output_dir \
	--num_train_epochs="5" \
	--per_device_train_batch_size="8" \
	--per_device_eval_batch_size="8" \
	--gradient_accumulation_steps="1" \
	--learning_rate="3e-4" \
	--warmup_steps="400" \
	--evaluation_strategy="steps" \
	--text_column_name="text" \
	--save_steps="400" \
	--eval_steps="400" \
	--logging_steps="10" \
	--save_total_limit="1" \
	--freeze_feature_extractor \
	--gradient_checkpointing \
	--fp16 \
	--group_by_length \
	--predict_with_generate \
	--do_train --do_eval