NbAiLab
/

whisper-tiny-nob

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

pere commited on Dec 15, 2022

Commit

2f27166

•

1 Parent(s): d0fd7a7

first

Files changed (1) hide show

run.sh +1 -1

run.sh CHANGED Viewed

@@ -8,7 +8,7 @@ python run_speech_recognition_seq2seq_streaming.py \
 	--max_steps="100000" \
 	--output_dir="./" \
 	--per_device_train_batch_size="128" \
-	--per_device_eval_batch_size="16" \
 	--gradient_accumulation_step="1" \
 	--logging_steps="50" \
 	--learning_rate="3e-6" \

 	--max_steps="100000" \
 	--output_dir="./" \
 	--per_device_train_batch_size="128" \
+	--per_device_eval_batch_size="32" \
 	--gradient_accumulation_step="1" \
 	--logging_steps="50" \
 	--learning_rate="3e-6" \