File size: 1,158 Bytes
73d6051
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
33
python run_speech_recognition_ctc.py \
        --dataset_name="/Data" \
        --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
        --dataset_config_name="ur" \
        --output_dir="./Model" \
        --overwrite_output_dir \
        --num_train_epochs="200" \
        --per_device_train_batch_size="32" \
        --per_device_eval_batch_size="8" \
        --gradient_accumulation_steps="2" \
        --learning_rate="1e-4" \
        --warmup_steps="1000" \
	--length_column_name="input_length" \
        --evaluation_strategy="steps" \
        --text_column_name="sentence" \
        --save_steps="500" \
        --eval_steps="500" \
        --logging_steps="500" \
        --layerdrop="0.0" \
        --activation_dropout="0.1" \
        --save_total_limit="2" \
        --freeze_feature_encoder \
        --feat_proj_dropout="0.0" \
        --mask_time_prob="0.75" \
        --mask_time_length="10" \
        --mask_feature_prob="0.25" \
        --mask_feature_length="64" \
	--chars_to_ignore ! ؛ ، ٫ ؟ ۔  ٪  " ' : - ‘ ’ \
        --gradient_checkpointing \
        --fp16 \
        --group_by_length \
        --do_train --do_eval