patrickvonplaten
/

wav2vec2-300m-mls-german-ft

Automatic Speech Recognition Transformers PyTorch TensorBoard

wav2vec2 multilingual_librispeech generated_from_trainer Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

patrickvonplaten commited on Nov 15, 2021

Commit

4bc929f

•

1 Parent(s): 4f8f3d3

Update run.sh

Files changed (1) hide show

run.sh +2 -3

run.sh CHANGED Viewed

@@ -1,7 +1,6 @@
 #!/usr/bin/env bash
-# python -m torch.distributed.launch \
-#        --nproc_per_node 2 run_speech_recognition_ctc.py \
-CUDA_VISIBLE_DEVICES="0" python run_speech_recognition_ctc.py \
 --dataset_name="multilingual_librispeech" \
 --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
 --train_split_name="train.9h" \

 #!/usr/bin/env bash
+python -m torch.distributed.launch \
+--nproc_per_node 2 run_speech_recognition_ctc.py \
 --dataset_name="multilingual_librispeech" \
 --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
 --train_split_name="train.9h" \