lucio
/

xls-r-kyrgiz-cv8

Automatic Speech Recognition

Generated from Trainer

hf-asr-leaderboard

mozilla-foundation/common_voice_8_0

robust-speech-event

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

lucio commited on Feb 5, 2022

Commit

5794a6e

•

1 Parent(s): 35656a6

run longer

Files changed (1) hide show

run.sh +1 -1

run.sh CHANGED Viewed

@@ -6,7 +6,7 @@ python ~/xls-r-kyrgiz-cv8/run_speech_recognition_ctc.py \
     --eval_split_name="validation[50%:]" \
 	--output_dir="./xls-r-kyrgiz-cv8" \
 	--overwrite_output_dir \
-	--num_train_epochs="50" \
 	--per_device_train_batch_size="32" \
 	--per_device_eval_batch_size="8" \
 	--gradient_accumulation_steps="4" \

     --eval_split_name="validation[50%:]" \
 	--output_dir="./xls-r-kyrgiz-cv8" \
 	--overwrite_output_dir \
+	--num_train_epochs="100" \
 	--per_device_train_batch_size="32" \
 	--per_device_eval_batch_size="8" \
 	--gradient_accumulation_steps="4" \