marinone94
/

whisper-tiny-sv

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions Community

marinone94 commited on Dec 14, 2022

Commit

b9efe48

·

1 Parent(s): 6ea4d4a

reduce max steps

Files changed (1) hide show

test_run_nordic.sh +1 -1

test_run_nordic.sh CHANGED Viewed

@@ -11,7 +11,7 @@ python $1run_speech_recognition_seq2seq_streaming.py \
 	--model_index_name="Whisper Tiny Swedish" \
 	--max_train_samples="64" \
 	--max_eval_samples="32" \
-	--max_steps="5000" \
 	--output_dir="./" \
 	--per_device_train_batch_size="8" \
 	--per_device_eval_batch_size="4" \

 	--model_index_name="Whisper Tiny Swedish" \
 	--max_train_samples="64" \
 	--max_eval_samples="32" \
+	--max_steps="500" \
 	--output_dir="./" \
 	--per_device_train_batch_size="8" \
 	--per_device_eval_batch_size="4" \