patrickvonplaten
/

hubert-librispeech-clean-100h-demo-dist

Automatic Speech Recognition

speech-recognition

librispeech_asr

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

patrickvonplaten commited on Oct 27, 2021

Commit

05313af

•

1 Parent(s): 9e7a1e3

Update run.sh

Files changed (1) hide show

run.sh +2 -2

run.sh CHANGED Viewed

@@ -2,11 +2,11 @@
 python -m torch.distributed.launch \
 	--nproc_per_node 8 run_speech_recognition_ctc.py \
 	--dataset_name="librispeech_asr" \
-	--model_name_or_path="facebook/hubert-large" \
 	--dataset_config_name="clean" \
 	--train_split_name="train.100" \
 	--eval_split_name="validation" \
-	--output_dir="./hubert-librispeech-clean-100h-demo-dist" \
 	--preprocessing_num_workers="16" \
 	--overwrite_output_dir \
 	--num_train_epochs="3" \

 python -m torch.distributed.launch \
 	--nproc_per_node 8 run_speech_recognition_ctc.py \
 	--dataset_name="librispeech_asr" \
+	--model_name_or_path="facebook/hubert-large-ll60k" \
 	--dataset_config_name="clean" \
 	--train_split_name="train.100" \
 	--eval_split_name="validation" \
+	--output_dir="./hubert-large-ll60k-librispeech-clean-100h-demo-dist" \
 	--preprocessing_num_workers="16" \
 	--overwrite_output_dir \
 	--num_train_epochs="3" \