ylacombe HF staff commited on
Commit
df5885a
1 Parent(s): febb19e

Create run.sh

Browse files
Files changed (1) hide show
  1. run.sh +34 -0
run.sh ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+ torchrun --nproc_per_node 3 examples/pytorch/speech-recognition/run_speech_recognition_ctc.py
3
+ --dataset_name="librispeech_asr" \
4
+ --model_name_or_path="facebook/w2v-bert-2.0" \
5
+ --dataset_config_name="clean" \
6
+ --eval_split_name="test" \
7
+ --train_split_name="train.100" \
8
+ --output_dir="./wav2vec2-bert-CV16-en-libri" \
9
+ --num_train_epochs="7" \
10
+ --per_device_train_batch_size="12" \
11
+ --gradient_accumulation_steps="2" \
12
+ --per_device_eval_batch_size="12" \
13
+ --learning_rate="3e-5" \
14
+ --warmup_steps="10000" \
15
+ --evaluation_strategy="steps" \
16
+ --text_column_name="text" \
17
+ --save_steps="500" \
18
+ --eval_steps="250" \
19
+ --save_total_limit="3" \
20
+ --gradient_checkpointing \
21
+ --chars_to_ignore , ? . ! - \; \: \" “ % ‘ ” \
22
+ --fp16 --push_to_hub \
23
+ --do_train --do_eval \
24
+ --eval_metrics "wer" "cer" \
25
+ --freeze_feature_encoder false --logging_steps "5" \
26
+ --add_adapter true \
27
+ --preprocessing_num_workers "32" \
28
+ --mask_time_prob="0.0" --mask_feature_prob="0.0" \
29
+ --tokenizer_name_or_path "jonatasgrosman/wav2vec2-large-xlsr-53-english" \
30
+ --eval_accumulation_steps "2" --group_by_length --length_column_name="input_length" \
31
+ --layerdrop="0.0" \
32
+ --hidden_dropout="0.05" --activation_dropout="0.05" --feat_proj_dropout="0.05"
33
+
34
+